An Empirical evaluation of zero resource acoustic unit discovery

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

An Empirical evaluation of zero resource acoustic unit discovery

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Publication year

2017

Confidentiality

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

Article name in the collection

Proceedings of ICASSP 2017

ISBN

978-1-5090-4117-6

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

5305-5309

Publisher name

IEEE Signal Processing Society

Place of publication

New Orleans

Event location

New Orleans, USA

Event date

Mar 5, 2017

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000414286205093