An Empirical evaluation of zero resource acoustic unit discovery

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F17%3APU126428" target="_blank" >RIV/00216305:26230/17:PU126428 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.fit.vut.cz/research/publication/11471/" target="_blank" >https://www.fit.vut.cz/research/publication/11471/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2017.7953169" target="_blank" >10.1109/ICASSP.2017.7953169</a>

Jazyk výsledku

angličtina

Název v původním jazyce

An Empirical evaluation of zero resource acoustic unit discovery

Popis výsledku v původním jazyce

Acoustic unit discovery (AUD) is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations. AUD provides an important avenue for unsupervised acoustic model training in a zero resource setting where expert-provided linguistic knowledge and transcribed speech are unavailable. Therefore, to further facilitate zero-resource AUD process, in this paper, we demonstrate acoustic feature representations can be significantly improved by (i) performing linear discriminant analysis (LDA) in an unsupervised self-trained fashion, and (ii) leveraging resources of other languages through building a multilingual bottleneck (BN) feature extractor to give effective cross-lingual generalization. Moreover, we perform comprehensive evaluations of AUD efficacy on multiple downstream speech applications, and their correlated performance suggests that AUD evaluations are feasible using different alternative language resources when only a subset of these evaluation resources can be available in typical zero resource applications.

Název v anglickém jazyce

An Empirical evaluation of zero resource acoustic unit discovery

Popis výsledku anglicky

Acoustic unit discovery (AUD) is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations. AUD provides an important avenue for unsupervised acoustic model training in a zero resource setting where expert-provided linguistic knowledge and transcribed speech are unavailable. Therefore, to further facilitate zero-resource AUD process, in this paper, we demonstrate acoustic feature representations can be significantly improved by (i) performing linear discriminant analysis (LDA) in an unsupervised self-trained fashion, and (ii) leveraging resources of other languages through building a multilingual bottleneck (BN) feature extractor to give effective cross-lingual generalization. Moreover, we perform comprehensive evaluations of AUD efficacy on multiple downstream speech applications, and their correlated performance suggests that AUD evaluations are feasible using different alternative language resources when only a subset of these evaluation resources can be available in typical zero resource applications.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of ICASSP 2017

ISBN

978-1-5090-4117-6

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

5305-5309

Název nakladatele

IEEE Signal Processing Society

Místo vydání

New Orleans

Místo konání akce

New Orleans, USA

Datum konání akce

5. 3. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000414286205093