Conference paper

BURGET Lukáš, DEHAK Najim, KESIRAJU Santosh, KHUDANPUR Sanjeev, ONDEL Lucas and YANG Jinyi. An Empirical evaluation of zero resource acoustic unit discovery. In: Proceedings of ICASSP 2017. New Orleans: IEEE Signal Processing Society, 2017, pp. 5305-5309. ISBN 978-1-5090-4117-6.
Publication language:english
Original title:An Empirical evaluation of zero resource acoustic unit discovery
Title (cs):Empirické hodnocení automatického hledání řečových jednotek bez popsaných trénovacích dat
Pages:5305-5309
Proceedings:Proceedings of ICASSP 2017
Conference:42nd IEEE International Conference on Acoustics, Speech and Signal Processing
Place:New Orleans, US
Year:2017
ISBN:978-1-5090-4117-6
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2017/liu_kesiraju_icassp2017_0005305.pdf [PDF]
Keywords
Acoustic unit discovery, unsupervised linear discriminant analysis, evaluation methods, zero resource
Annotation
This article is about an empirical evaluation of zero resource acoustic unit discovery (AUD), which is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations.
Abstract
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.
BibTeX:
@INPROCEEDINGS{
   author = {Luk{\'{a}}{\v{s}} Burget and Najim Dehak and Santosh
	Kesiraju and Sanjeev Khudanpur and Lucas Ondel and Jinyi
	Yang},
   title = {An Empirical evaluation of zero resource acoustic unit
	discovery},
   pages = {5305--5309},
   booktitle = {Proceedings of ICASSP 2017},
   year = {2017},
   location = {New Orleans, US},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-5090-4117-6},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=11471}
}

Your IPv4 address: 54.224.49.217
Switch to IPv6 connection

DNSSEC [dnssec]