Change search
ReferencesLink to record
Permanent link

Direct link
Using HMMs and ANNs for mapping acoustic to visual speech
KTH, Superseded Departments, Speech, Music and Hearing.ORCID iD: 0000-0002-3323-5311
1999 (English)In: TMH-QPSR, Vol. 40, no 1-2, 45-50 p.Article in journal (Other academic) Published
Abstract [en]

In this paper we present two different methods for mapping auditory, telephonequality speech to visual parameter trajectories, specifying the movements of ananimated synthetic face. In the first method, Hidden Markov Models (HMMs)where used to obtain phoneme strings and time labels. These where thentransformed by rules into parameter trajectories for visual speech synthesis. In thesecond method, Artificial Neural Networks (ANNs) were trained to directly mapacoustic parameters to synthesis parameters. Speaker independent HMMs weretrained on a phonetically transcribed telephone speech database. Differentunderlying units of speech were modelled by the HMMs, such as monophones,diphones, triphones, and visemes. The ANNs were trained on male, female , andmixed speakers.The HMM method and the ANN method were evaluated through audio-visualintelligibility tests with ten hearing impaired persons, and compared to “ideal”articulations (where no recognition was involved), a natural face, and to theintelligibility of the audio alone. It was found that the HMM method performsconsiderably better than the audio alone condition (54% and 34% keywordscorrect, respectively), but not as well as the “ideal” articulating artificial face(64%). The intelligibility for the ANN method was 34% keywords correct.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 1999. Vol. 40, no 1-2, 45-50 p.
National Category
Computer Science
URN: urn:nbn:se:kth:diva-6150OAI: diva2:10779

QC 20100630. QC 20160211

Available from: 2006-09-21 Created: 2006-09-21 Last updated: 2016-02-11Bibliographically approved
In thesis
1. Mining Speech Sounds: Machine Learning Methods for Automatic Speech Recognition and Analysis
Open this publication in new window or tab >>Mining Speech Sounds: Machine Learning Methods for Automatic Speech Recognition and Analysis
2006 (English)Doctoral thesis, comprehensive summary (Other scientific)
Abstract [en]

This thesis collects studies on machine learning methods applied to speech technology and speech research problems. The six research papers included in this thesis are organised in three main areas.

The first group of studies were carried out within the European project Synface. The aim was to develop a low latency phonetic recogniser to drive the articulatory movements of a computer generated virtual face from the acoustic speech signal. The visual information provided by the face is used as hearing aid for persons using the telephone.

Paper A compares two solutions to the problem of mapping acoustic to visual information that are based on regression and classification techniques. Recurrent Neural Networks are used to perform regression while Hidden Markov Models are used for the classification task. In the second case the visual information needed to drive the synthetic face is obtained by interpolation between target values for each acoustic class. The evaluation is based on listening tests with hearing impaired subjects were the intelligibility of sentence material is compared in different conditions: audio alone, audio and natural face, audio and synthetic face driven by the different methods.

Paper B analyses the behaviour, in low latency conditions, of a phonetic recogniser based on a hybrid of Recurrent Neural Networks (RNNs) and Hidden Markov Models (HMMs). The focus is on the interaction between the time evolution model learnt by the RNNs and the one imposed by the HMMs.

Paper C investigates the possibility of using the entropy of the posterior probabilities estimated by a phoneme classification neural network, as a feature for phonetic boundary detection. The entropy and its time evolution are analysed with respect to the identity of the phonetic segment and the distance from a reference phonetic boundary.

In the second group of studies, the aim was to provide tools for analysing large amount of speech data in order to study geographical variations in pronunciation (accent analysis).

Paper D and Paper E use Hidden Markov Models and Agglomerative Hierarchical Clustering to analyse a data set of about 100 millions data points (5000 speakers, 270 hours of speech recordings). In Paper E, Linear Discriminant Analysis was used to determine the features that most concisely describe the groupings obtained with the clustering procedure.

The third group belongs to studies carried out during the international project MILLE (Modelling Language Learning) that aims at investigating and modelling the language acquisition process in infants.

Paper F proposes the use of an incremental form of Model Based Clustering to describe the unsupervised emergence of phonetic classes in the first stages of language acquisition. The experiments were carried out on child-directed speech expressly collected for the purposes of the project

Place, publisher, year, edition, pages
Stockholm: KTH, 2006. xix, 87 p.
Trita-CSC-A, ISSN 1653-5723 ; 2006:12
speech, machine learning, data mining, signal processing
National Category
Computer Science
urn:nbn:se:kth:diva-4111 (URN)91-7178-446-2 (ISBN)
Public defence
2006-10-06, F3, Sing Sing, Lindstedtsvägen 26, Stockholm, 13:00
QC 20100630Available from: 2006-09-21 Created: 2006-09-21 Last updated: 2010-06-30Bibliographically approved

Open Access in DiVA

No full text

Other links

Dept. for Speech, Music and Hearing

Search in DiVA

By author/editor
Salvi, Giampiero
By organisation
Speech, Music and Hearing
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 35 hits
ReferencesLink to record
Permanent link

Direct link