Publication Details
An Empirical evaluation of zero resource acoustic unit discovery
Yang Jinyi (JHU)
Sun Ming (AmazonCom)
Kesiraju Santosh (DCGM FIT BUT)
Rott Alena (USTAN)
Ondel Yang Lucas Antoine Francois, Mgr., Ph.D. (DCGM FIT BUT)
Ghahremani Pegah (JHU)
Dehak Najim (JHU)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Khudanpur Sanjeev (JHU)
Acoustic unit discovery, unsupervised linear discriminant analysis, evaluation methods, zero resource
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.
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.
@INPROCEEDINGS{FITPUB11471,
author = "Chunxi Liu and Jinyi Yang and Ming Sun and Santosh Kesiraju and Alena Rott and Francois Antoine Lucas Yang 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 = "https://www.fit.vut.cz/research/publication/11471"
}