On Acquiring Speech Production Knowledge from Articulatory Measurements for Phoneme Recognition
2009 (English)In: INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, BAIXAS: ISCA-INST SPEECH COMMUNICATION ASSOC , 2009, 1387-1390 p.Conference paper (Refereed)
The paper proposes a general version of a coupled Hidden Markov/Bayesian Network model for performing phoneme recognition on acoustic-articulatory data. The model uses knowledge learned from the articulatory measurements, available for training, for phoneme recognition on the acoustic input. After training on the articulatory data, the model is able to predict 71.5% of the articulatory state sequences using the acoustic input. Using optimized parameters, the proposed method shows a slight improvement for two speakers over the baseline phoneme recognition system which does not use articulatory knowledge. However, the improvement is only statistically significant for one of the speakers. While there is an improvement in recognition accuracy for the vowels, diphthongs and to some extent the semi-vowels, there is a decrease in accuracy for the remaining phonemes.
Place, publisher, year, edition, pages
BAIXAS: ISCA-INST SPEECH COMMUNICATION ASSOC , 2009. 1387-1390 p.
phoneme recognition, articulatory measurements, Coupled-HMM
Computer and Information Science General Language Studies and Linguistics
IdentifiersURN: urn:nbn:se:kth:diva-29882ISI: 000276842800344ScopusID: 2-s2.0-70450202220OAI: oai:DiVA.org:kth-29882DiVA: diva2:399061
10th INTERSPEECH 2009 Conference, Brighton, ENGLAND, SEP 06-10, 2009
QC 201102212011-02-212011-02-172011-02-21Bibliographically approved