Článek ve sborníku konference

LIU Chunxi, YANG Jinyi, SUN Ming, KESIRAJU Santosh, ROTT Alena, ONDEL Lucas, GHAHREMANI Pegah, DEHAK Najim, BURGET Lukáš a KHUDANPUR Sanjeev. An Empirical evaluation of zero resource acoustic unit discovery. In: Proceedings of ICASSP 2017. New Orleans: IEEE Signal Processing Society, 2017, s. 5305-5309. ISBN 978-1-5090-4117-6.
Jazyk publikace:angličtina
Název publikace:An Empirical evaluation of zero resource acoustic unit discovery
Název (cs):Empirické hodnocení automatického hledání řečových jednotek bez popsaných trénovacích dat
Strany:5305-5309
Sborník:Proceedings of ICASSP 2017
Konference:42nd IEEE International Conference on Acoustics, Speech and Signal Processing
Místo vydání:New Orleans, US
Rok:2017
ISBN:978-1-5090-4117-6
DOI:10.1109/ICASSP.2017.7953169
Vydavatel:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2017/liu_kesiraju_icassp2017_0005305.pdf [PDF]
Klíčová slova
Acoustic unit discovery, unsupervised linear discriminant analysis, evaluation methods, zero resource
Anotace
Článek pojednává o empirickém hodnocení automatického hledání řečových jednotek bez popsaných trénovacích dat.
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.
BibTeX:
@INPROCEEDINGS{
   author = {Chunxi Liu and Jinyi Yang and Ming Sun and Santosh
	Kesiraju and Alena Rott and Lucas Ondel and Pegah
	Ghahremani and Najim Dehak and Luk{\'{a}}{\v{s}}
	Burget and Sanjeev Khudanpur},
   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},
   doi = {10.1109/ICASSP.2017.7953169},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.cs.iso-8859-2?id=11471}
}

Vaše IPv4 adresa: 18.232.124.77