Detail publikace

Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery

ONDEL YANG, L. VYDANA, H. BURGET, L. ČERNOCKÝ, J.

Originální název

Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

Bayesian Inference, Hidden Markov Model, Subspace Model, Variational Bayes, Low-resource languages, Acoustic Unit Discovery

Autoři

ONDEL YANG, L.; VYDANA, H.; BURGET, L.; ČERNOCKÝ, J.

Vydáno

15. 9. 2019

Nakladatel

International Speech Communication Association

Místo

Graz

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Ročník

2019

Číslo

9

Stát

Francouzská republika

Strany od

261

Strany do

265

Strany počet

5

URL

https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2224.pdf

BibTex

@inproceedings{BUT159991,
  author="Lucas Antoine Francois {Ondel} and Hari Krishna {Vydana} and Lukáš {Burget} and Jan {Černocký}",
  title="Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery",
  booktitle="Proceedings of Interspeech 2019",
  year="2019",
  journal="Proceedings of Interspeech",
  volume="2019",
  number="9",
  pages="261--265",
  publisher="International Speech Communication Association",
  address="Graz",
  doi="10.21437/Interspeech.2019-2224",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2224.pdf"
}