Non-Parametric Bayesian Subspace Models for Acoustic Unit Discovery

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU144939" target="_blank" >RIV/00216305:26230/22:PU144939 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9767690" target="_blank" >https://ieeexplore.ieee.org/document/9767690</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TASLP.2022.3171975" target="_blank" >10.1109/TASLP.2022.3171975</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Non-Parametric Bayesian Subspace Models for Acoustic Unit Discovery

Popis výsledku v původním jazyce

This work investigates subspace non-parametric models for the task of learning a set of acoustic units fromunlabeled speech recordings. We constrain the base-measure of a Dirichlet- Process mixture with a phonetic subspaceestimated from other source languagesto build an educated prior, thereby forcing the learned acoustic units to resemble phones of known source languages. Two types of models are proposed: (i) the Subspace HMM (SHMM) which assumes that the phonetic subspace is the same for every language, (ii) the Hierarchical-Subspace HMM (H-SHMM) which relaxes this assumption and allows to have a languagespecific subspace estimated on the unlabeled target data. These models are applied on 3 languages: English, Yoruba and Mboshi and they are compared with various competitive acoustic units discovery baselines. Experimental results show that both subspace models outperform other systems in terms of clustering quality and segmentation accuracy. Moreover, we observe that the H-SHMM provides results superior to the SHMM supporting the idea that language-specific priors are preferable to language-agnostic priors for acoustic unit discovery.

Název v anglickém jazyce

Non-Parametric Bayesian Subspace Models for Acoustic Unit Discovery

Popis výsledku anglicky

This work investigates subspace non-parametric models for the task of learning a set of acoustic units fromunlabeled speech recordings. We constrain the base-measure of a Dirichlet- Process mixture with a phonetic subspaceestimated from other source languagesto build an educated prior, thereby forcing the learned acoustic units to resemble phones of known source languages. Two types of models are proposed: (i) the Subspace HMM (SHMM) which assumes that the phonetic subspace is the same for every language, (ii) the Hierarchical-Subspace HMM (H-SHMM) which relaxes this assumption and allows to have a languagespecific subspace estimated on the unlabeled target data. These models are applied on 3 languages: English, Yoruba and Mboshi and they are compared with various competitive acoustic units discovery baselines. Experimental results show that both subspace models outperform other systems in terms of clustering quality and segmentation accuracy. Moreover, we observe that the H-SHMM provides results superior to the SHMM supporting the idea that language-specific priors are preferable to language-agnostic priors for acoustic unit discovery.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GX19-26934X" target="_blank" >GX19-26934X: Neuronové reprezentace v multimodálním a mnohojazyčném modelování</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING

ISSN

2329-9290

e-ISSN

2329-9304

Svazek periodika

30

Číslo periodika v rámci svazku

5

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

1902-1917

Kód UT WoS článku

000811572000001

EID výsledku v databázi Scopus

2-s2.0-85129456463