Detail publikačního výsledku

An Empirical evaluation of zero resource acoustic unit discovery

LIU, C.; YANG, J.; SUN, M.; KESIRAJU, S.; ROTT, A.; ONDEL YANG, L.; GHAHREMANI, P.; DEHAK, N.; BURGET, L.; KHUDANPUR, S.

Originální název

An Empirical evaluation of zero resource acoustic unit discovery

Anglický název

An Empirical evaluation of zero resource acoustic unit discovery

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

Acoustic unit discovery, unsupervised lineardiscriminant analysis, evaluation methods, zero resource

Klíčová slova v angličtině

Acoustic unit discovery, unsupervised lineardiscriminant analysis, evaluation methods, zero resource

Autoři

LIU, C.; YANG, J.; SUN, M.; KESIRAJU, S.; ROTT, A.; ONDEL YANG, L.; GHAHREMANI, P.; DEHAK, N.; BURGET, L.; KHUDANPUR, S.

Rok RIV

2018

Vydáno

05.03.2017

Nakladatel

IEEE Signal Processing Society

Místo

New Orleans

ISBN

978-1-5090-4117-6

Kniha

Proceedings of ICASSP 2017

Strany od

5305

Strany do

5309

Strany počet

5

URL

https://www.fit.vut.cz/research/publication/11471/

Plný text v Digitální knihovně

http://hdl.handle.net/

BibTex

@inproceedings{BUT144451,
  author="Chunxi {Liu} and Jinyi {Yang} and Ming {Sun} and Santosh {Kesiraju} and Alena {Rott} and Lucas Antoine Francois {Ondel} and Pegah {Ghahremani} and Najim {Dehak} and Lukáš {Burget} and Sanjeev {Khudanpur}",
  title="An Empirical evaluation of zero resource acoustic unit discovery",
  booktitle="Proceedings of ICASSP 2017",
  year="2017",
  pages="5305--5309",
  publisher="IEEE Signal Processing Society",
  address="New Orleans",
  doi="10.1109/ICASSP.2017.7953169",
  isbn="978-1-5090-4117-6",
  url="https://www.fit.vut.cz/research/publication/11471/"
}

Dokumenty

liu_kesiraju_icassp2017_0005305