Faculty of Information Technology, BUT

Publication Details

Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery

ONDEL Lucas, VYDANA Hari K., BURGET Lukáš and ČERNOCKÝ Jan. Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery. In: Proceedings of Interspeech 2019. Graz: International Speech Communication Association, 2019, pp. 261-265. ISSN 1990-9772. Available from: https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2224.pdf
Czech title
Bayesovský podprostorový skrytý Markovův model pro objevování akustických jednotek
Type
conference paper
Language
english
Authors
Ondel Lucas, Mgr. (DCGM FIT BUT)
Vydana Hari K. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, doc. Dr. Ing. (DCGM FIT BUT)
URL
Keywords
Bayesian Inference, Hidden Markov Model, Subspace Model, Variational Bayes, Low-resource languages, Acoustic Unit Discovery
Abstract
This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages. Our approach may be described by the following two steps procedure: first the model learns the notion of acoustic units from the labelled data and then the model uses its knowledge to find new acoustic units on the target language. We implement this process with the Bayesian Subspace Hidden Markov Model (SHMM), a model akin to the Subspace Gaussian Mixture Model (SGMM) where each low dimensional embedding represents an acoustic unit rather than just a HMMs state. The subspace is trained on 3 languages from the GlobalPhone corpus (German, Polish and Spanish) and the AUs are discovered on the TIMIT corpus. Results, measured in equivalent Phone Error Rate, show that this approach significantly outperforms previous HMM based acoustic units discovery systems and compares favorably with the Variational Auto Encoder-HMM.
Published
2019
Pages
261-265
Journal
Proceedings of Interspeech, vol. 2019, no. 9, ISSN 1990-9772
Proceedings
Proceedings of Interspeech 2019
Conference
INTERSPEECH 2019, INTERSPEECH 2019, AT
Publisher
International Speech Communication Association
Place
Graz, AT
DOI
BibTeX
@INPROCEEDINGS{FITPUB12084,
   author = "Lucas Ondel and K. Hari Vydana and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery",
   pages = "261--265",
   booktitle = "Proceedings of Interspeech 2019",
   journal = "Proceedings of Interspeech",
   volume = 2019,
   number = 9,
   year = 2019,
   location = "Graz, AT",
   publisher = "International Speech Communication Association",
   ISSN = "1990-9772",
   doi = "10.21437/Interspeech.2019-2224",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12084"
}
Back to top