Change search
Refine search result
1 - 45 of 45
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the 'Create feeds' function.
  • 1. Benetos, Emmanouil
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Automatic Transcription of Turkish Makam Music2013In: Proceedings of ISMIR - International Conference on Music Information Retrieval, International Society for Music Information Retrieval, 2013, 355-360 p.Conference paper (Refereed)
    Abstract [en]

    In this paper we propose an automatic system for transcribing makam music of Turkey. We document the specific traits of this music that deviate from properties that were targeted by transcription tools so far and we compile a dataset of makam recordings along with aligned microtonal ground-truth. An existing multi-pitch detection algorithm is adapted for transcribing music in 20 cent resolution, and the final transcription is centered around the tonic frequency of the recording. Evaluation metrics for transcribing microtonal music are utilized and results show that transcription of Turkish makam music in e.g. an interactive transcription software is feasible using the current state-of-the-art.

  • 2. Benetos, Emmanouil
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Automatic transcription of Turkish microtonal music2015In: Journal of the Acoustical Society of America, ISSN 0001-4966, Vol. 138, no 4, 2118-2130 p.Article in journal (Refereed)
    Abstract [en]

    Automatic music transcription, a central topic in music signal analysis, is typically limited to equal-tempered music and evaluated on a quartertone tolerance level. A system is proposed to automatically transcribe microtonal and heterophonic music as applied to the makam music of Turkey. Specific traits of this music that deviate from properties targeted by current transcription tools are discussed, and a collection of instrumental and vocal recordings is compiled, along with aligned microtonal reference pitch annotations. An existing multi-pitch detection algorithm is adapted for transcribing music with 20 cent resolution, and a method for converting a multi-pitch heterophonic output into a single melodic line is proposed. Evaluation metrics for transcribing microtonal music are applied, which use various levels of tolerance for inaccuracies with respect to frequency and time. Results show that the system is able to transcribe microtonal instrumental music at 20 cent resolution with an F-measure of 56.7%, outperforming state-of-the-art methods for the same task. Case studies on transcribed recordings are provided, to demonstrate the shortcomings and the strengths of the proposed method.

  • 3. Benetos, Emmanouil
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Incorporating pitch class profiles for improving automatic transcription of Turkish makam music2014In: Proceedings of the 4th Workshop on Folk Music Analysis, Computer Engineering Department, Bogaziçi University , 2014, 15-20 p.Conference paper (Refereed)
    Abstract [en]

    In this paper we evaluate the impact of including knowledge about scale material into a system for the transcription of Turkish makam music. To this end, we extend our previously presented appoach by a refinement iteration that gives preference to note values present in the scale of the mode (i.e. makam). The information about the scalar material is provided in form of pitch class profiles, and they are imposed in form of a Dirichlet prior to our expanded probabilistic latent component analysis (PLCA) transcription system. While the inclusion of such a prior was supposed to focus the transcription system on musically meaningful areas, the obtained results are significantly improved only for recordings of certain instruments. In our discussion we demonstrate the quality of the obtained transcriptions, and discuss the difficulties caused for evaluation in the context of microtonal music.

  • 4. Benetos, Emmanouil
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Stylianou, Yannis
    Pitched Instrument Onset Detection Based on Auditory Spectra2009In: Proceedings of ISMIR - International Conference on Music Information Retrieval, 2009, 105-110 p.Conference paper (Refereed)
    Abstract [en]

    In this paper, a novel method for onset detection of music signals using auditory spectra is proposed. The auditory spectrogram provides a time-frequency representation that employs a sound processing model resembling the human auditory system. Recent work on onset detection employs DFT-based features, such as the spectral flux and group delay function. The spectral flux and group delay are introduced in the auditory framework and an onset detection algorithm is proposed. Experiments are conducted on a dataset covering 11pitched instrument types, consisting of 1829 onsets in total. Results indicate the superiority of the auditory representations over the DFT-based ones, with the auditory spectral flux exhibiting an onset detection improvement by 2% in terms of F-measure when compared to the DFT-based feature.

  • 5. Bozkurt, Baris
    et al.
    Ayangil, Ruhi
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Computational analysis of makam music in Turkey: review of state-of-the-art and challenges2014In: Journal for New Music Research, ISSN 0929-8215, Vol. 43, no 1, 3-23 p.Article in journal (Refereed)
    Abstract [en]

    This text targets a review of the computational analysis literature for Turkish makam music, discussing in detail the challenges involved and presenting a perspective for further studies. For that purpose, the basic concepts of Turkish makam music and the description of melodic, rhythmic and timbral aspects are considered in detail. Studies on tuning analysis, automatic transcription, automatic melodic analysis, automatic makam and usul detection are reviewed. Technological and data resource needs for further advancement are discussed and available sources are presented.

  • 6. Cornelis, Olmo
    et al.
    Six, Joren
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Leman, Marc
    Evaluation and Recommendation of Pulse and Tempo Annotation in Ethnic Music2013In: Journal for New Music Research, ISSN 0929-8215, Vol. 42, no 2, 131-149 p.Article in journal (Refereed)
    Abstract [en]

    Large digital archives of ethnic music require automatic tools to provide musical content descriptions. While various automatic approaches are available, they are to a wide extent developed for Western popular music. This paper aims to analyse how automated tempo estimation approaches perform in the context of Central-African music. To this end we collect human beat annotations for a set of musical fragments, and compare them with automatic beat tracking sequences. We first analyse the tempo estimations derived from annotations and beat tracking results. Then we examine an approach, based on mutual agreement between automatic and human annotations, to automate such analysis, which can serve to detect musical fragments with high tempo ambiguity.

  • 7. d’Alessandro, N.
    et al.
    Babacan, O.
    Bozkurt, B.
    Dubuisson, T.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Kessous, L.
    Moinet, A.
    Vlieghe, M.
    Dutoit, T.
    RAMCESS 2.x FRAMEWORK - EXPRESSIVE VOICE ANALYSIS FOR REALTIME AND ACCURATE SYNTHESIS OF SINGING2008In: Journal on Multimodal User Interfaces, ISSN 1783-7677, Vol. 2, 133-144 p.Article in journal (Refereed)
    Abstract [en]

    In this paper we present the work that has been achieved in the context of the second version of the RAMCESS singing synthesis framework. The main improvement of this study is the integration of new algorithms for expressive voice analysis, especially the separation of the glottal source and the vocal tract. Realtime synthesis modules have also been refined. These elements have been integrated in an existing digital instrument: the HANDSKETCH 1.X, a bimanual controller. Moreover this digital instrument is compared to existing systems.

  • 8. Dutoit, T.
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Jottrand, M.
    Moinet, A.
    Perez, J.
    Stylianou, Y.
    Towards a voice conversion system based on frame selection2007In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE Press, 2007, Vol. IV, 513-516 p.Conference paper (Refereed)
    Abstract [en]

    The subject of this paper is the conversion of a given speaker's voice (the source speaker) into another identified voice (the target one). We assume we have at our disposal a large amount of speech samples from source and target voice with at least a part of them being parallel. The proposed system is built on a mapping function between source and target spectral envelopes followed by a frame selection algorithm to produce final spectral envelopes. Converted speech is produced by a basic LP analysis of the source and LP synthesis using the converted spectral envelopes. We compared three types of conversion: without mapping, with mapping and using the excitation of the source speaker and finally with mapping using the excitation of the target. Results show that the combination of mapping and frame selection provide the best results, and underline the interest to work on methods to convert the LP excitation.

  • 9. Dzhambazov, Georgi
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Srinivasamurthy, Ajay
    Serra, Xavier
    Metrical-accent Aware Vocal Onset Detection in Polyphonic Audio2017Conference paper (Refereed)
    Abstract [en]

    The goal of this study is the automatic detection of onsets of the singing voice in polyphonic audio recordings. Starting with a hypothesis that the knowledge of the current position in a metrical cycle (i.e. metrical accent) can improve the accuracy of vocal note onset detection, we propose a novel probabilistic model to jointly track beats and vocal note onsets. The proposed model extends a state of the art model for beat and meter tracking, in which a-priori probability of a note at a specific metrical accent interacts with the probability of observing a vocal note onset. We carry out an evaluation on a varied collection of multi-instrument datasets from two music traditions (English popular music and Turkish makam) with different types of metrical cycles and singing styles. Results confirm that the proposed model reasonably improves vocal note onset detection accuracy compared to a baseline model that does not take metrical position into account.

  • 10. Fossum, Dave
    et al.
    Holzapfel, André
    Bogazici University, Istanbul.
    Exploring the Music of Two Masters of the Turkmen Dutar Through Timing Analysis2014In: Proceedings of the 4th Workshop on Folk Music Analysis, Bogaziçi University , 2014, 52-56 p.Conference paper (Refereed)
    Abstract [en]

    In this paper, we analyze onset characteristics to try to identify important differences between two famous Turkmen dutar performers in terms of patterns of timing. We first analyzed annotated onset data for equivalent excerpts from recordings by these two musicians. We then analyzed unannotated onset data for a larger set of entire recordings. These analyses showed several conclusions. First, during introductory strumming outside the context of a composed melody, the two have different timing habits. Mylly aga is more consistent and Purli aga more varied ¨ in terms of recurring inter-onset-intervals (IOIs). Second, during through-composed melodies, the timing profiles of the two musicians are very similar. This perhaps reflects the traditional Turkmen emphasis on preserving the form of traditional compositions in great detail and the attention paid to strumming technique. Finally, we found that automatically derived representations of rhythmic patterns, referred to as pulsation matrices, could be useful for identifying departures from typical timing patterns, which we could then analyze in order to understand such variations and their possible significance

  • 11.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    A corpus study on rhythmic modes in Turkish makam music and their interaction with meter2015In: Proceedings of the 15. Congress of the Society for Music Theory, 2015Conference paper (Refereed)
  • 12.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Computational Analysis of Melodic Motives in Cretan Leaping Dances: Motivations, Perspectives, and Limitations2015Conference paper (Other academic)
  • 13.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Leaping dances in Crete: Tradition in motion2014Conference paper (Other academic)
    Abstract [en]

    Throughout the last decades a new enthusiasm for local music and an increasing trend towards rediscovering old local dances and tunes gained momentum in the island of Crete. In the presented analysis I combine an ethnographic with a comparative approach, driven by audio signal analysis tools, in order to address the question of how far tunes that serve to define local and micro-local identities differ in certain aspects with regard to the sound of performances. For this I investigate three sound aspects of Cretan leaping dance performances: tempo, rhythmic stress patterns, and contained melodic patterns. I accompany the analytical results with information obtained from my interviews with dancing teachers and musicians. My results depict small but significant differences depending on the dance, but also underline the great homogeneity of the repertoire. The results imply that all three aspects contribute to the fine differences between the dance tunes, with a clear emphasis on the melodic phrases. Therefore, this study with its findings and its computational tools paves the way towards the establishment of dictionaries of characteristic melodic phrases of Cretan dance repertoire, as well as of dance tunes with similar morphology.

  • 14.
    Holzapfel, André
    Bogazici University.
    Melodic key phrases in traditional Cretan dance tunes2015In: Proceedings of the 5th International Workshop on Folk Music Analysis, Institut Jean le Rond d'Alembert , 2015, 79-82 p.Conference paper (Refereed)
  • 15.
    Holzapfel, André
    Bogaziçi University, Turkey.
    Relation between surface rhythm and rhythmic modes in Turkish makam music2015In: Journal of New Music Research, ISSN 0929-8215, E-ISSN 1744-5027, Vol. 44, no 1, 25-38 p.Article in journal (Refereed)
    Abstract [en]

    Sounds in a piece of music form rhythmic patterns on the surface of a music signal, and in a metered piece these patterns stand in some relation to the underlying rhythmic mode or meter. In this paper, we investigate how the surface rhythm is related to the usul, which are the rhythmic modes in compositions of Turkish makam music. On a large corpus of notations of vocal pieces in short usul we observe the ways notes are distributed in relation to the usul. We observe differences in these distributions between Turkish makam and Eurogenetic music, which imply a less accentuated stratification of meter in Turkish makam music. We observe changes in rhythmic style between two composers who represent two different historical periods in Turkish makam music, a result that adds to previous observations on changes in style of Turkish makam music throughout the centuries. We demonstrate that rhythmic aspects in Turkish makam music can be considered as the outcome of a generative model, and conduct style comparisons in a Bayesian statistical framework.

  • 16.
    Holzapfel, André
    Bogazici University, Turkey.
    TEMPO AND PROSODY IN TURKISH TAKSIM IMPROVISATION2013In: Proceedings of the 3rd Workshop on Folk Music Analysis, Meertens Institute; Department of Information and Computing Sciences, Utrecht University , 2013, 1-6 p.Conference paper (Refereed)
    Abstract [en]

    Instrumental improvisation in Turkish makam music, the taksim, is considered to be free-rhythm, that is its rhythm develops without the underlying template of a meter or continuous organized pulsation. In this paper, we want to examine how in this setting, rhythmic idioms are formed and maintained throughout a performance. For this, we will apply a simple signal processing approach. We show differences that can be observed between performers, and raise the question if a tempo could be evoked by certain regularities in the occurring rhythmic elaborations.

  • 17.
    Holzapfel, André
    et al.
    Austrian Research Institute for Artificial Intelligence (OFAI).
    Benetos, Emmanouil
    The Sousta corpus: Beat-informed automatic transcription of traditional dance tunes2016In: Proceedings of ISMIR - International Conference on Music Information Retrieval, 2016, 531-537 p.Conference paper (Refereed)
    Abstract [en]

    In this paper, we present a new corpus for research in computational ethnomusicology and automatic music transcription, consisting of traditional dance tunes from Crete. This rich dataset includes audio recordings, scores transcribed by ethnomusicologists and aligned to the audio performances, and meter annotations. A second contribution of this paper is the creation of an automatic music transcription system able to support the detection of multiple pitches produced by lyra (a bowed string instrument). Furthermore, the transcription system is able to cope with deviations from standard tuning, and provides temporally quantized notes by combining the output of the multi-pitch detection stage with a state-of-the-art meter tracking algorithm. Experiments carried out for note tracking using 25ms onset tolerance reach 41.1% using information from the multi-pitch detection stage only, 54.6% when integrating beat information, and 57.9% when also supporting tuning estimation. The produced meter aligned transcriptions can be used to generate staff notation, a fact that increases the value of the system for studies in ethnomusicologyIn this paper, we present a new corpus for research in computational ethnomusicology and automatic music transcription, consisting of traditional dance tunes from Crete. This rich dataset includes audio recordings, scores transcribed by ethnomusicologists and aligned to the audio performances, and meter annotations. A second contribution of this paper is the creation of an automatic music transcription system able to support the detection of multiple pitches produced by lyra (a bowed string instrument). Furthermore, the transcription system is able to cope with deviations from standard tuning, and provides temporally quantized notes by combining the output of the multi-pitch detection stage with a state-of-the-art meter tracking algorithm. Experiments carried out for note tracking using 25ms onset tolerance reach 41.1% using information from the multi-pitch detection stage only, 54.6% when integrating beat information, and 57.9% when also supporting tuning estimation. The produced meter aligned transcriptions can be used to generate staff notation, a fact that increases the value of the system for studies in ethnomusicology

  • 18.
    Holzapfel, André
    et al.
    Universitat Pompeu Fabra Barcelona, Spain.
    Bozkurt, Baris
    Metrical Strength and Contradiction in Turkish Makam Music2012In: Proceedings of the 2nd CompMusic Workshop, 2012, 79-84 p.Conference paper (Other academic)
    Abstract [en]

    In this paper we investigate how note onsets in Turkish Makam music compositions are distributed, and in how far this distribution supports or contradicts the metrical structure of the pieces, the usul. We use MIDI data to derive the distributions in the form of onset histograms, and compare them with metrical weights that are applied to describe the usul in theory. We compute correlation and syncopation values to estimate the degrees of support and contradiction, respectively. While the concept of syncopation is rarely mentioned in the context of this music, we can gain interesting insight into the structure of a piece using such a measure. We show that metrical contradiction is systematically applied in some metrical structures. We will compare the differences between Western music and Turkish Makam music regarding metrical support and contradiction. Such a study can help avoiding pitfalls in later attempts to perform audio processing tasks such as beat tracking or rhythmic similarity measurements.

  • 19.
    Holzapfel, André
    et al.
    Universitat Pompeu Fabra, Spain .
    Davies, Matthew E. P.
    Zapata, José R.
    Oliveira, Joao Lobato
    Gouyon, Fabien
    Selective sampling for beat tracking evaluation2012In: IEEE Transactions on Audio, Speech, and Language Processing, ISSN 1558-7916, E-ISSN 1558-7924, Vol. 20, no 9, 2539-2548 p.Article in journal (Refereed)
    Abstract [en]

    In this paper, we propose a method that can identify challenging music samples for beat tracking without ground truth. Our method, motivated by the machine learning method "selective sampling," is based on the measurement of mutual agreement between beat sequences. In calculating this mutual agreement we show the critical influence of different evaluation measures. Using our approach we demonstrate how to compile a new evaluation dataset comprised of difficult excerpts for beat tracking and examine this difficulty in the context of perceptual and musical properties. Based on tag analysis we indicate the musical properties where future advances in beat tracking research would be most profitable and where beat tracking is too difficult to be attempted. Finally, we demonstrate how our mutual agreement method can be used to improve beat tracking accuracy on large music collections.

  • 20.
    Holzapfel, André
    et al.
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Davies, Matthew
    Zapata, Jose Ricardo
    Oliveira, Joao Lobato
    Gouyon, Fabien
    On the automatic identification of difficult examples for beat tracking: towards building new evaluation datasets2012In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE conference proceedings, 2012, 89-92 p.Conference paper (Refereed)
    Abstract [en]

    In this paper, an approach is presented that identifies music samples which are difficult for current state-of-the-art beat trackers. In order to estimate this difficulty even for examples without ground truth, a method motivated by selective sampling is applied. This method assigns a degree of difficulty to a sample based on the mutual disagreement between the output of various beat tracking systems. On a large beat annotated dataset we show that this mutual agreement is correlated with the mean performance of the beat trackers evaluated against the ground truth, and hence can be used to identify difficult examples by predicting poor beat tracking performance. Towards the aim of advancing future beat tracking systems, we demonstrate how our method can be used to form new datasets containing a high proportion of challenging music examples.

  • 21.
    Holzapfel, André
    et al.
    Austrian Research Institute for Artificial Intelligence (OFAI).
    Flexer, Arthur
    Widmer, Gerhard
    Improving tempo-sensitive and tempo-robust descriptors for rhythmic similarity2011In: Proceedings of the Conference on Sound and Music Computing (SMC), Sound and music Computing network , 2011Conference paper (Refereed)
    Abstract [en]

    For the description of rhythmic content of music signals usually features are preferred that are invariant in presence of tempo changes. In this paper it is shown that the importance oftempo depends on the musical context. For popular music, a tempo-sensitive feature is improved on multiple datasets using analysis of variance, and it is shown that also a tempo-robust description profits from the integration into the resulting processing framework. Important insights are given into optimal parameters for rhythm description, and limitations of current approaches are indicated.

  • 22.
    Holzapfel, André
    et al.
    Austrian Research Institute for Artificial Intelligence (OFAI).
    Grill, Thomas
    Bayesian meter tracking on learned signal representations2016In: Proceedings of ISMIR - International Conference on Music Information Retrieval, ISMIR , 2016, 262-268 p.Conference paper (Refereed)
    Abstract [en]

    Most music exhibits a pulsating temporal structure, known as meter. Consequently, the task of meter tracking is of great importance for the domain of Music Information Retrieval. In our contribution, we specifically focus on Indian art musics, where meter is conceptualized at several hierarchical levels, and a diverse variety of metrical hierarchies exist, which poses a challenge for state of the art analysis methods. To this end, for the first time, we combine Convolutional Neural Networks (CNN), allowing to transcend manually tailored signal representations, with subsequent Dynamic Bayesian Tracking (BT), modeling the recurrent metrical structure in music. Our approach estimates meter structures simultaneously at two metrical levels. The results constitute a clear advance in meter tracking performance for Indian art music, and we also demonstrate that these results generalize to a set of Ballroom dances. Furthermore, the incorporation of neural network output allows a computationally efficient inference. We expect the combination of learned signal representations through CNNs and higher-level temporal modeling to be applicable to all styles of metered music, provided the availability of sufficient training data.

  • 23.
    Holzapfel, André
    et al.
    New York University Abu Dhabi.
    Krebs, Florian
    Srinivasamurthy, Ajay
    Tracking the “odd”: Meter inference in a culturally diverse music corpus2014In: Proceedings of ISMIR - International Conference on Music Information Retrieval, ISMIR , 2014, 425-430 p.Conference paper (Refereed)
    Abstract [en]

    In this paper, we approach the tasks of beat tracking, downbeat recognition and rhythmic style classification in nonWestern music. Our approach is based on a Bayesian model, which infers tempo, downbeats and rhythmic style, from an audio signal. The model can be automatically adapted to rhythmic styles and time signatures. For evaluation, we compiled and annotated a music corpus consisting of eight rhythmic styles from three cultures, containing a variety of meter types. We demonstrate that by adapting the model to specific styles, we can track beats and downbeats in odd meter types like 9/8 or 7/8 with an accuracy significantly improved over the state of the art. Even if the rhythmic style is not known in advance, a unified model is able to recognize the meter and track the beat with comparable results, providing a novel method for inferring the metrical structure in culturally diverse datasets.

  • 24.
    Holzapfel, André
    et al.
    Bogazici University, Turkey.
    Simsekli, Umut
    Sentürk, Sertan
    Cemgil, Ali Taylan
    Section-level modeling of musical audio for linking performances to scores in Turkish makam music2015In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE conference proceedings, 2015, 141-145 p.Conference paper (Refereed)
    Abstract [en]

    Section linking aims at relating structural units in the notation of a piece of music to their occurrences in a performance of the piece. In this paper, we address this task by presenting a score-informed hierarchical Hidden Markov Model (HHMM) for modeling musical audio signals on the temporal level of sections present in a composition, where the main idea is to explicitly model the long range and hierarchical structure of music signals. So far, approaches based on HHMM or similar methods were mainly developed for a note-to-note alignment, i.e. an alignment based on shorter temporal units than sections. Such approaches, however, are conceptually problematic when the performances differ substantially from the reference score due to interpretation and improvisation, a very common phenomenon, for instance, in Turkish makam music. In addition to having low computational complexity compared to note-to-note alignment and achieving a transparent and elegant model, the experimental results show that our method outperforms a previously presented approach on a Turkish makam music corpus.

  • 25.
    Holzapfel, André
    et al.
    University of Crete.
    Stylianou, Yannis
    A scale transform based method for rhythmic similarity of music2009In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE conference proceedings, 2009, 317-320 p.Conference paper (Refereed)
    Abstract [en]

    This paper introduces scale transforms to measure rhythmic similarity between two musical pieces. The rhythm of a piece of music is described by the scale transform magnitude, computed by transforming the sample autocorrelation of its onset strength signal to the scale domain. Then, two pieces can be compared without the impact of tempo differences by using simple distances between these descriptors like the cosine distance. A widely used dance music dataset has been chosen for proof of concept. On this data set, the proposed method based on scale transform achieves classification results as high as other state of the art approaches. On a second data set, which is characterized by much larger intra-class tempo variance, the scale transform based measure improves classification compared to previously presented measures by 41%.

  • 26.
    Holzapfel, André
    et al.
    University of Crete.
    Stylianou, Yannis
    A statistical approach to musical genre classification using Non-negative Matrix Factorization2007In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE Press, 2007, Vol. II, 693-696 p.Conference paper (Refereed)
    Abstract [en]

    This paper introduces a new feature set based on a Non-negtive Matrix Factorization approach for the classification of musical signals into genres, only using synchronous organization of music events (vertical dimension of music). This feature set generates a vector space to describe the spectrogram representation of a music Signal. The space is modeled statistically by a mixture of Gaussians (GMM). A new signal is classified by considering the likelihoods over all the estimated feature vectors given these statistical models, without constructing a model for the signal itself. Cross-validation tests on two commonly utilized datasets for this task show the superiority of the proposed features compared to the widely used MFCC type of representation based on classification accuracies (over 9% of improvement), as well as on a stability measure introduced in this paper for GMM.

  • 27.
    Holzapfel, André
    et al.
    University of Crete.
    Stylianou, Yannis
    Beat tracking using group delay based onset detection2008In: Proceedings of ISMIR - International Conference on Music Information Retrieval, ISMIR , 2008, 653-658 p.Conference paper (Refereed)
    Abstract [en]

    This paper introduces a novel approach to estimate onsets in musical signals based on the phase spectrum and specifically using the average of the group delay function. A frame-by-frame analysis of a music signal provides the evolution of group delay over time, referred to as phase slope function. Onsets are then detected simply by locating the positive zero-crossings of the phase slope function. The proposed approach is compared to an amplitude-based onset detection approach in the framework of a state-of-the-art system for beat tracking. On a data set of music with less percussive content, the beat tracking accuracy achieved by the system is improved by 82% when the suggested phase-based onset detection approach is used instead of the amplitudebased approach, while on a set of music with stronger percussive characteristics both onset detection approaches provide comparable results of accuracy.

  • 28.
    Holzapfel, André
    et al.
    Institute of Computer Science.
    Stylianou, Yannis
    Musical genre classification using Nonnegative Matrix Factorization based features2008In: IEEE Transactions on Audio, Speech, and Language Processing, ISSN 1558-7916, E-ISSN 1558-7924, Vol. 16, no 2, 424-434 p.Article in journal (Refereed)
    Abstract [en]

    Nonnegative matrix factorization (NMF) is used to derive a novel description for the timbre of musical sounds. Using NMF, a spectrogram is factorized providing a characteristic spectral basis. Assuming a set of spectrograms given a musical genre, the space spanned by the vectors of the obtained spectral bases is modeled statistically using mixtures of Gaussians, resulting in a description of the spectral base for this musical genre. This description is shown to improve classification results by up to 23.3% compared to MFCC-based models, while the compression performed by the factorization decreases training time significantly. Using a distance-based stability measure this compression is shown to reduce the noise present in the data set resulting in more stable classification models. In addition, we compare the mean squared errors of the approximation to a spectrogram using independent component analysis and nonnegative matrix factorization, showing the superiority of the latter approach.

  • 29.
    Holzapfel, André
    et al.
    University of Crete.
    Stylianou, Yannis
    Parataxis: Morphological similarity in traditional music2010In: Proceedings of ISMIR - International Conference on Music Information Retrieval, ISMIR , 2010, 453-458 p.Conference paper (Refereed)
    Abstract [en]

    In this paper an automatic system for the detection of similar phrases in music of the Eastern Mediterranean is proposed. This music follows a specific structure, which is referred to as parataxis. The proposed system can be applied to audio signals of complex mixtures that contain the lead melody together with instrumental accompaniment. It is shown that including a lead melody estimation into a stateof-the-art system for cover song detection leads to promising results on a dataset of transcribed traditional dances from the island of Crete in Greece. Furthermore, a general framework that includes also rhythmic aspects is proposed. The proposed method represents a simple framework for the support of ethnomusicological studies on related forms of traditional music.

  • 30.
    Holzapfel, André
    et al.
    University of Crete.
    Stylianou, Yannis
    Rhythmic Similarity in Traditional Turkish Music2009In: Proceedings of ISMIR - International Conference on Music Information Retrieval, ISMIR , 2009, 99-104 p.Conference paper (Refereed)
    Abstract [en]

    In this paper, the problem of automatically assigning a piece of traditional Turkish music into a class of rhythm referred to as usul is addressed. For this, an approach for rhythmic similarity measurement based on scale transforms has been evaluated on a set of MIDI data. Because this task is related to time signature estimation, the accuracy of the proposed method is evaluated and compared with a state of the art time signature estimation approach. The results indicate that the proposed method can be successfully applied to audio signals of Turkish music and that it captures relevant properties of the individual usul.

  • 31.
    Holzapfel, André
    et al.
    Technological Education Institute, Greece.
    Stylianou, Yannis
    Scale transform in rhythmic similarity of music2011In: IEEE Transactions on Audio, Speech, and Language Processing, ISSN 1558-7916, E-ISSN 1558-7924, Vol. 19, no 1, 176-185 p.Article in journal (Refereed)
    Abstract [en]

    As a special case of the Mellin transform, the scale transform has been applied in various signal processing areas, in order to get a signal description that is invariant to scale changes. In this paper, the scale transform is applied to autocorrelation sequences derived from music signals. It is shown that two such sequences, when derived from similar rhythms with different tempo, differ mainly by a scaling factor. By using the scale transform, the proposed descriptors are robust to tempo changes, and are specially suited for the comparison of pieces with different tempi but similar rhythm. As music with such characteristics is widely encountered in traditional forms of music, the performance of the descriptors in a classification task of Greek traditional dances and Turkish traditional songs is evaluated. On these datasets accuracies compared to non-tempo robust approaches are improved by more than 20%, while on a dataset of Western music the achieved accuracy improves compared to previously presented results.

  • 32.
    Holzapfel, André
    et al.
    Institute of Computer Science, FORTH, Greece.
    Stylianou, Yannis
    Singer Identification in Rembetiko Music2007In: Proceedings of the Conference on Sound and Music Computing (SMC), Sound and music Computing network , 2007, 326-329 p.Conference paper (Refereed)
    Abstract [en]

    In this paper, the problem of the automatic identification of a singer is investigated using methods known from speaker identification. Ways for using world models are presented and the usage of Cepstral Mean Subtraction (CMS) is evaluated. In order to minimize the difference due to musical style we use a novel data set, consisting of samples from greekRembetiko music, being very similar in style. The data set also explores for the first time the influence of the recording quality, by including many historical gramophone recordings. Experimental evaluations show the benefits of world models for frame selection and CMS, resulting in an average classification accuracy of about 81% among 21 different singers.

  • 33.
    Holzapfel, André
    et al.
    Institute of Computer Science; University of Crete, Greece.
    Stylianou, Yannis
    Gedik, Ali C.
    Bozkurt, Baris
    Three dimensions of pitched instrument onset detection2010In: IEEE Transactions on Audio, Speech, and Language Processing, ISSN 1558-7916, E-ISSN 1558-7924, Vol. 18, no 6, 1517-1527 p.Article in journal (Refereed)
    Abstract [en]

    In this paper, we suggest a novel group delay based method for the onset detection of pitched instruments. It is proposed to approach the problem of onset detection by examining three dimensions separately: phase (i.e., group delay), magnitude and pitch. The evaluation of the suggested onset detectors for phase, pitch and magnitude is performed using a new publicly available and fully onset annotated database of monophonic recordings which is balanced in terms of included instruments and onset samples per instrument, while it contains different performance styles. Results show that the accuracy of onset detection depends on the type of instruments as well as on the style of performance. Combining the information contained in the three dimensions by means of a fusion at decision level leads to an improvement of onset detection by about 8% in terms of F-measure, compared to the best single dimension.

  • 34.
    Holzapfel, André
    et al.
    INESC Porto, Portugal.
    Velasco, Gino Angelo
    Holighaus, Nicki
    Dörfler, Monika
    Flexer, Arthur
    Advantages of nonstationary Gabor transforms in beat tracking2011In: MIRUM ’11 Proceedings of the 1st international ACM workshop on Music information retrieval with user-centered and multimodal strategies, ACM Press, 2011, 45-50 p.Conference paper (Refereed)
    Abstract [en]

    In this paper the potential of using nonstationary Gabor transform for beat tracking in music is examined. Nonstationary Gabor transforms are a generalization of the short-time Fourier transform, which allow flexibility in choosing the number of bins per octave, while retaining a perfect inverse transform. In this paper, it is evaluated if these properties can lead to an improved beat tracking in music signals, thus presenting an approach that introduces recent findings in mathematics to music information retrieval. For this, both nonstationaryGabor transforms and short-time Fourier transform are integrated into a simple beat tracking framework. Statistically significant improvements are observed on a large dataset, which motivates to integrate the nonstationary Gabor transform into state of the art approaches for beat tracking and tempo estimation.

  • 35. Karaosmano\uglu, M. Kemal
    et al.
    Bozkurt, Baris
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Dicsiaçik, Nilgün Dougrusöz
    A symbolic dataset of Turkish makam music phrases2014In: Proceedings of the 4th International Workshop on Folk Music Analysis, 2014, 10-14 p.Conference paper (Refereed)
    Abstract [en]

    One of the basic needs for computational studies of traditional music is the availability of free datasets. This study presents a large machine-readable dataset of Turkish makam music scores segmented into phrases by experts of this music. The segmentation facilitates computational research on melodic similarity between phrases, and relation between melodic phrasing and meter, rarely studied topics due to unavailability of data resources.

  • 36. Krebs, Florian
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Cemgil, Ali Taylan
    Widmer, Gerhard
    Inferring metrical structure in music using particle filters2015In: IEEE Transactions on Audio, Speech and Language Processing, ISSN 2329-9290, Vol. 23, no 5, 817-827 p.Article in journal (Refereed)
    Abstract [en]

    In this paper, we propose a new state-of-the-art particle filter (PF) system to infer the metrical structure of musical audio signals. The new inference method is designed to overcome the problem of PFs in multi-modal probability distributions, which arise due to tempo and phase ambiguities in musical rhythm representations. We compare the new method with a hidden Markov model (HMM) system and several other PF schemes in terms of performance, speed and scalability on several audio datasets. We demonstrate that using the proposed system the computational complexity can be reduced drastically in comparison to the HMM while maintaining the same order of beat tracking accuracy. Therefore, for the first time, the proposed system allows fast meter inference in a high-dimensional state space, spanned by the three components of tempo, type of rhythm, and position in a metric cycle.

  • 37. Markaki, Maria
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Stylianou, Yannis
    Singing Voice Detection using Modulation Frequency Features2008In: Proceedings of ISCA Tutorial and Research Workshop on Statistical and Perceptual Audition (SAPA), 2008, 7-10 p.Conference paper (Refereed)
    Abstract [en]

    In this paper, a feature set derived from modulation spectra is applied to the task of detecting singing voice in historical and recent recordings of Greek Rembetiko. A generalization of SVD to tensors, Higher Order SVD (HOSVD), is applied to reduce the dimensions of the feature vectors. Projection onto the “significant” principal axes of the acoustic and modulation frequency subspaces, results in a compact feature set, which is evaluated using an SVM classifier on a set of hand labeled musical mixtures. Fusion of the proposed features with MFCCs and delta coefficients reduces the optimal detection cost from 11.11% to 9.01%.

  • 38. Miron, Marius
    et al.
    Gouyon, Fabien
    Davies, Matthew E.P.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Beat Station: A real-time rhythm annotation software2013In: Proceedings of Sound and Music Computing Conference (SMC) 2013, Sound and Music Computing , 2013, 729-734 p.Conference paper (Refereed)
    Abstract [en]

    This paper describes an open-source software for real-time rhythm annotation. The software integrates several modules for graphical user interface, user management across a network, tap recording, audio playing, midi interfacing and threading. It is a powerful tool for conducting listening tests, but can also be used for beat annotation of music or in a game setup. The parameters of this software, including the real-time constraints, are not pre-defined in the code but can be easily changed in a settings file. Finally, the framework used allows for scalability, as it was developed in openFrameworks. We show the usefulness of the software by applying it in a cross-cultural beat tapping experiment during the ISMIR 2012 conference. An analysis of the collected real-time annotations indicates that listeners encounter difficulties in synchronizing to music in presence of unfamiliar rhythmic structures and instrumental timbres.

  • 39. Panagiotakis, Costas
    et al.
    Holzapfel, André
    Universitat Pompeu Fabra, Spain.
    Michel, Damien
    Argyros, Antonis
    Beat synchronous dance animation based on visual analysis of human motion and audio analysis of music tempo2013In: Advances in Visual Computing: 9th International Symposium, ISVC 2013, Rethymnon, Crete, Greece, July 29-31, 2013. Proceedings, Part II, Springer Berlin/Heidelberg, 2013, Vol. 8034, 118-127 p.Conference paper (Refereed)
    Abstract [en]

    We present a framework that generates beat synchronous dance animation based on the analysis of both visual and audio data. First, the articulated motion of a dancer is captured based on markerless visual observations obtained by a multicamera system. We propose and employ a new method for the temporal segmentation of such motion data into the periods of dance. Next, we use a beat tracking algorithm to estimate the pulse related to the tempo of a piece of music. Given an input music that is of the same genre as the one corresponding to the visually observed dance, we automatically produce a beat synchronous dance animation of a virtual character. The proposed approach has been validated with extensive experiments performed on a data set containing a variety on traditional Greek/Cretan dances and the corresponding music.

  • 40. Sioros, George
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Guedes, Carlos
    On measuring syncopation to drive an interactive music system2012In: Proceedings of the 13th International Society for Music Information Retrieval Conference (ISMIR 2012), 2012, 283-288 p.Conference paper (Refereed)
  • 41. Srinivasamurthy, Ajay
    et al.
    Holzapfel, Andre
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Cemgil, Ali Taylan
    Serra, Xavier
    Particle Filters for Efficient Meter Tracking with Dynamic Bayesian Networks2015In: Proceedings of ISMIR - International Society for Music Information Retrieval Conference, 2015Conference paper (Refereed)
  • 42. Srinivasamurthy, Ajay
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Cemgil, Ali Taylan
    Serra, Xavier
    A generalized Bayesian model for tracking long metrical cycles in acoustic music signals2016In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, 76-80 p., 7471640Conference paper (Refereed)
    Abstract [en]

    Most musical phenomena involve repetitive structures that enable listeners to track meter, i.e. The tactus or beat, the longer over-arching measure or bar, and possibly other related layers. Meters with long measure duration, sometimes lasting more than a minute, occur in many music cultures, e.g. from India, Turkey, and Korea. However, current meter tracking algorithms, which were devised for cycles of a few seconds length, cannot process such structures accurately. We present a novel generalization to an existing Bayesian model for meter tracking that overcomes this limitation. The proposed model is evaluated on a set of Indian Hindustani music recordings, and we document significant performance increase over the previous models. The presented model opens the way for computational analysis of performances with long metrical cycles, and has important applications in music studies as well as in commercial applications that involve such musics.

  • 43. Srinivasamurthy, Ajay
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Serra, Xavier
    In Search of Automatic Rhythm Analysis Methods for Turkish and Indian Art Music2014In: Journal for New Music Research, ISSN 0929-8215, Vol. 43, no 1, 94-114 p.Article in journal (Refereed)
    Abstract [en]

    The aim of this paper is to identify and discuss various methods in computational rhythm description of Carnatic and Hindustani music of India, and Makam music of Turkey. We define and describe three relevant rhythm annotation tasks for these cultures-beat tracking, meter estimation, and downbeat detection. We then evaluate several methodologies from the state of the art in Music Information Retrieval (MIR) for these tasks, using manually annotated datasets of Turkish and Indian music. This evaluation provides insights into the nature of rhythm in these cultures and the challenges to automatic rhythm analysis. Our results indicate that the performance of evaluated approaches is not adequate for the presented tasks, and that methods that are suitable to tackle the culture specific challenges in computational analysis of rhythm need to be developed. The results from the different analysis methods enable us to identify promising directions for an appropriate exploration of rhythm analysis in Turkish, Carnatic and Hindustani music.

  • 44. Zapata, Jose Ricardo
    et al.
    Davies, Matthew E. P.
    Holzapfel, Andre
    Oliveira, Joao L.
    Gouyon, Fabien
    Assigning a confidence threshold on automatic beat annotation in large datasets2012In: Proceedings of ISMIR - International Conference on Music Information Retrieval, 2012, 157-162 p.Conference paper (Refereed)
    Abstract [en]

    In this paper we establish a threshold for perceptually acceptable beat tracking based on the mutual agreement of a committee of beat trackers. In the first step we use an existing annotated dataset to show that mutual agreement can be used to select one committee member as the most reliable beat tracker for a song. Then we conduct a listening test using a subset of the Million Song Dataset to establish a threshold which results in acceptable quality of the chosen beat output. For both datasets, we obtain a percent age of trackable music of about 73%, and we investigate which data tags are related to acceptable and problematic beat tracking. The results indicate that current datasets are biased towards genres which tend to be easy for beat tracking. The proposed methods provide a means to automatically obtain a confidence value for beat tracking in non-annotated data and to choose between a number of beat tracker outputs.

  • 45. Şentürk, Sertan
    et al.
    Holzapfel, André
    KTH, School of Computer Science and Communication (CSC), Media Technology and Interaction Design, MID.
    Serra, Xavier
    Linking Scores and Audio Recordings in Makam Music of Turkey2014In: Journal for New Music Research, ISSN 0929-8215, Vol. 43, no 1, 34-52 p.Article in journal (Refereed)
    Abstract [en]

    The most relevant representations of music are notations and audio recordings, each of which emphasizes a particular perspective and promotes different approximations in the analysis and understanding of music. Linking these two representations and analysing them jointly should help to better study many musical facets by being able to combine complementary analysis methodologies. In order to develop accurate linking methods, we have to take into account the specificities of a given type of music. In this paper, we present a method for linking musically relevant sections in a score of a piece from makam music of Turkey (MMT) to the corresponding time intervals of an audio recording of the same piece. The method starts by extracting relevant features from the score and from the audio recording. The features of a given score section are compared with the features of the audio recording to find the candidate links in the audio for that score section. Next, using the sequential section information stored in the score, it selects the most likely links. The method is tested on a dataset consisting of instrumental and vocal compositions of MMT, achieving 92.1% and 96.9% F-1-scores on the instrumental and vocal pieces, respectively. Our results show the importance of culture-specific and knowledge-based approaches in music information processing.

1 - 45 of 45
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf