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 specificacoustic units from unlabeled speech recordings given aset of labeled recordings from other languages. Our approachmay be described by the following two steps procedure: firstthe model learns the notion of acoustic units from the labelleddata and then the model uses its knowledge to find new acousticunits on the target language. We implement this processwith the Bayesian Subspace Hidden Markov Model (SHMM), amodel akin to the Subspace Gaussian Mixture Model (SGMM)where each low dimensional embedding represents an acousticunit rather than just a HMMs state. The subspace is trainedon 3 languages from the GlobalPhone corpus (German, Polishand Spanish) and the AUs are discovered on the TIMIT corpus.Results, measured in equivalent Phone Error Rate, show thatthis approach significantly outperforms previous HMM basedacoustic units discovery systems and compares favorably withthe 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
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"
}
Dokumenty