kth.sePublications
Change search
Refine search result
1 - 8 of 8
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • 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)
  • Disputation date (earliest first)
  • Disputation date (latest 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)
  • Disputation date (earliest first)
  • Disputation date (latest 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.
    Cumbal, Ronald
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Axelsson, Agnes
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Mehta, Shivam
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Engwall, Olov
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Stereotypical nationality representations in HRI: perspectives from international young adults2023In: Frontiers in Robotics and AI, E-ISSN 2296-9144, Vol. 10, article id 1264614Article in journal (Refereed)
    Abstract [en]

    People often form immediate expectations about other people, or groups of people, based on visual appearance and characteristics of their voice and speech. These stereotypes, often inaccurate or overgeneralized, may translate to robots that carry human-like qualities. This study aims to explore if nationality-based preconceptions regarding appearance and accents can be found in people's perception of a virtual and a physical social robot. In an online survey with 80 subjects evaluating different first-language-influenced accents of English and nationality-influenced human-like faces for a virtual robot, we find that accents, in particular, lead to preconceptions on perceived competence and likeability that correspond to previous findings in social science research. In a physical interaction study with 74 participants, we then studied if the perception of competence and likeability is similar after interacting with a robot portraying one of four different nationality representations from the online survey. We find that preconceptions on national stereotypes that appeared in the online survey vanish or are overshadowed by factors related to general interaction quality. We do, however, find some effects of the robot's stereotypical alignment with the subject group, with Swedish subjects (the majority group in this study) rating the Swedish-accented robot as less competent than the international group, but, on the other hand, recalling more facts from the Swedish robot's presentation than the international group does. In an extension in which the physical robot was replaced by a virtual robot interacting in the same scenario online, we further found the same results that preconceptions are of less importance after actual interactions, hence demonstrating that the differences in the ratings of the robot between the online survey and the interaction is not due to the interaction medium. We hence conclude that attitudes towards stereotypical national representations in HRI have a weak effect, at least for the user group included in this study (primarily educated young students in an international setting).

  • 2.
    Deichler, Anna
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Mehta, Shivam
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Alexanderson, Simon
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Beskow, Jonas
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Difusion-Based Co-Speech Gesture Generation Using Joint Text and Audio Representation2023In: PROCEEDINGS OF THE 25TH INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, ICMI 2023, Association for Computing Machinery (ACM) , 2023, p. 755-762Conference paper (Refereed)
    Abstract [en]

    This paper describes a system developed for the GENEA (Generation and Evaluation of Non-verbal Behaviour for Embodied Agents) Challenge 2023. Our solution builds on an existing difusion-based motion synthesis model. We propose a contrastive speech and motion pretraining (CSMP) module, which learns a joint embedding for speech and gesture with the aim to learn a semantic coupling between these modalities. The output of the CSMP module is used as a conditioning signal in the difusion-based gesture synthesis model in order to achieve semantically-aware co-speech gesture generation. Our entry achieved highest human-likeness and highest speech appropriateness rating among the submitted entries. This indicates that our system is a promising approach to achieve human-like co-speech gestures in agents that carry semantic meaning.

  • 3.
    Lameris, Harm
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Mehta, Shivam
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Henter, Gustav Eje
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH. KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.
    Gustafsson, Joakim
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Székely, Éva
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Prosody-Controllable Spontaneous TTS with Neural HMMs2023In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers (IEEE) , 2023Conference paper (Refereed)
    Abstract [en]

    Spontaneous speech has many affective and pragmatic functions that are interesting and challenging to model in TTS. However, the presence of reduced articulation, fillers, repetitions, and other disfluencies in spontaneous speech make the text and acoustics less aligned than in read speech, which is problematic for attention-based TTS. We propose a TTS architecture that can rapidly learn to speak from small and irregular datasets, while also reproducing the diversity of expressive phenomena present in spontaneous speech. Specifically, we add utterance-level prosody control to an existing neural HMM-based TTS system which is capable of stable, monotonic alignments for spontaneous speech. We objectively evaluate control accuracy and perform perceptual tests that demonstrate that prosody control does not degrade synthesis quality. To exemplify the power of combining prosody control and ecologically valid data for reproducing intricate spontaneous speech phenomena, we evaluate the system’s capability of synthesizing two types of creaky voice.

    Download full text (pdf)
    fulltext
  • 4.
    Lameris, Harm
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Mehta, Shivam
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Henter, Gustav Eje
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Kirkland, Ambika
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Moëll, Birger
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    O'Regan, Jim
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Gustafsson, Joakim
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Székely, Éva
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Spontaneous Neural HMM TTS with Prosodic Feature Modification2022In: Proceedings of Fonetik 2022, 2022Conference paper (Other academic)
    Abstract [en]

    Spontaneous speech synthesis is a complex enterprise, as the data has large variation, as well as speech disfluencies nor-mally omitted from read speech. These disfluencies perturb the attention mechanism present in most Text to Speech (TTS) sys-tems. Explicit modelling of prosodic features has enabled intu-itive prosody modification of synthesized speech. Most pros-ody-controlled TTS, however, has been trained on read-speech data that is not representative of spontaneous conversational prosody. The diversity in prosody in spontaneous speech data allows for more wide-ranging data-driven modelling of pro-sodic features. Additionally, prosody-controlled TTS requires extensive training data and GPU time which limits accessibil-ity. We use neural HMM TTS as it reduces the parameter size and can achieve fast convergence with stable alignments for spontaneous speech data. We modify neural HMM TTS to ena-ble prosodic control of the speech rate and fundamental fre-quency. We perform subjective evaluation of the generated speech of English and Swedish TTS models and objective eval-uation for English TTS. Subjective evaluation showed a signif-icant improvement in naturalness for Swedish for the mean prosody compared to a baseline with no prosody modification, and the objective evaluation showed greater variety in the mean of the per-utterance prosodic features.

  • 5.
    Mehta, Shivam
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH. Department of Industrial and Materials Science, Chalmers University of Technology, Rannvagen 2A, Göteborg, 41296 Sweden, Rännvägen 2A.
    Frisk, K.
    Department of Industrial and Materials Science, Chalmers University of Technology, Rannvagen 2A, Göteborg, 41296 Sweden, Rännvägen 2A.
    Nyborg, L.
    Department of Industrial and Materials Science, Chalmers University of Technology, Rannvagen 2A, Göteborg, 41296 Sweden, Rännvägen 2A.
    Role of Cr in Mn-rich precipitates for Al–Mn–Cr–Zr-based alloys tailored for additive manufacturing2024In: Calphad, ISSN 0364-5916, E-ISSN 1873-2984, Vol. 84, article id 102667Article in journal (Refereed)
    Abstract [en]

    Novel alloy concepts enabled via additive manufacturing processes have opened up the possibility of tailoring properties beyond the scope of conventional casting and powder metallurgy processes. The authors have previously presented a novel Al–Mn–Cr–Zr-based alloy system containing three times the equilibrium amounts of Mn and Zr. The alloys were produced via a powder bed fusion-laser beam (PBF-LB) process taking advantage of rapid cooling and solidification characteristics of the process. This supersaturation can then be leveraged to provide high precipitation hardening via direct ageing heat treatments. The hardening is enabled with Zr-rich and Mn-rich precipitates. Literature study confirms that Mn-rich precipitates have a notable solubility of Cr, for example, the Al12Mn precipitate. This study aims to clarify the effect of Cr solubility in the thermodynamics and kinetics simulation and compare the precipitation simulations with samples subject to >1000 h isothermal heat treatment, thus creating an equilibrium-like state. The results show that Cr addition to the precipitates stabilizes the Al12Mn precipitate while slowing the precipitation kinetics thus producing a favourable hardening response. Such observations could be insightful while designing such alloys and optimising heat treatments of the current or even a future alloy system.

  • 6.
    Mehta, Shivam
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Kirkland, Ambika
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Lameris, Harm
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Beskow, Jonas
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Székely, Éva
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Henter, Gustav Eje
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    OverFlow: Putting flows on top of neural transducers for better TTS2023In: Interspeech 2023, International Speech Communication Association , 2023, p. 4279-4283Conference paper (Refereed)
    Abstract [en]

    Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence modelling in text-to-speech. They combine the best features of classic statistical speech synthesis and modern neural TTS, requiring less data and fewer training updates, and are less prone to gibberish output caused by neural attention failures. In this paper, we combine neural HMM TTS with normalising flows for describing the highly non-Gaussian distribution of speech acoustics. The result is a powerful, fully probabilistic model of durations and acoustics that can be trained using exact maximum likelihood. Experiments show that a system based on our proposal needs fewer updates than comparable methods to produce accurate pronunciations and a subjective speech quality close to natural speech.

  • 7.
    Mehta, Shivam
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Székely, Éva
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Beskow, Jonas
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Henter, Gustav Eje
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Neural HMMs are all you need (for high-quality attention-free TTS)2022In: 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE Signal Processing Society, 2022, p. 7457-7461Conference paper (Refereed)
    Abstract [en]

    Neural sequence-to-sequence TTS has achieved significantly better output quality than statistical speech synthesis using HMMs. However, neural TTS is generally not probabilistic and uses non-monotonic attention. Attention failures increase training time and can make synthesis babble incoherently. This paper describes how the old and new paradigms can be combined to obtain the advantages of both worlds, by replacing attention in neural TTS with an autoregressive left-right no-skip hidden Markov model defined by a neural network. Based on this proposal, we modify Tacotron 2 to obtain an HMM-based neural TTS model with monotonic alignment, trained to maximise the full sequence likelihood without approximation. We also describe how to combine ideas from classical and contemporary TTS for best results. The resulting example system is smaller and simpler than Tacotron 2, and learns to speak with fewer iterations and less data, whilst achieving comparable naturalness prior to the post-net. Our approach also allows easy control over speaking rate.

  • 8.
    Moell, Birger
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    O'Regan, Jim
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Mehta, Shivam
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Kirkland, Ambika
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Lameris, Harm
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Gustafsson, Joakim
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Beskow, Jonas
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Speech Data Augmentation for Improving Phoneme Transcriptions of Aphasic Speech Using Wav2Vec 2.0 for the PSST Challenge2022In: The RaPID4 Workshop: Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments / [ed] Dimitrios Kokkinakis, Charalambos K. Themistocleous, Kristina Lundholm Fors, Athanasios Tsanas, Kathleen C. Fraser, Marseille, France, 2022, p. 62-70Conference paper (Refereed)
    Abstract [en]

    As part of the PSST challenge, we explore how data augmentations, data sources, and model size affect phoneme transcription accuracy on speech produced by individuals with aphasia. We evaluate model performance in terms of feature error rate (FER) and phoneme error rate (PER). We find that data augmentations techniques, such as pitch shift, improve model performance. Additionally, increasing the size of the model decreases FER and PER. Our experiments also show that adding manually-transcribed speech from non-aphasic speakers (TIMIT) improves performance when Room Impulse Response is used to augment the data. The best performing model combines aphasic and non-aphasic data and has a 21.0% PER and a 9.2% FER, a relative improvement of 9.8% compared to the baseline model on the primary outcome measurement. We show that data augmentation, larger model size, and additional non-aphasic data sources can be helpful in improving automatic phoneme recognition models for people with aphasia.

    Download full text (pdf)
    fulltext
1 - 8 of 8
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • 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