Conference paper

ROHDIN Johan A., STAFYLAKIS Themos, SILNOVA Anna, ZEINALI Hossein, BURGET Lukáš and PLCHOT Oldřich. Speaker Verification Using End-To-End Adversarial Language Adaptation. In: Proceedings of ICASSP 2019. Brighton: IEEE Signal Processing Society, 2019, pp. 6006-6010. ISBN 978-1-5386-4658-8. Available from:
Publication language:english
Original title:Speaker Verification Using End-To-End Adversarial Language Adaptation
Title (cs):Rozpoznávání mluvčího pomocí end-to-end kontradiktorní adaptace na jazyk
Proceedings:Proceedings of ICASSP 2019
Conference:International Conference on Acoustics, Speech, and Signal Processing
Place:Brighton, GB
Publisher:IEEE Signal Processing Society
Speaker recognition, domain adaptation
In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at minimizing certain divergences between the distribution that the utterance-level features follow (i.e. speaker embeddings) when drawn from source and target domains (i.e. languages), while preserving their capacity in recognizing speakers. Neural architectures for extracting utterancelevel representations enable us to apply adversarial adaptation methods in an end-to-end fashion and train the network jointly with the standard cross-entropy loss. We examine several configurations, such as the use of (pseudo-)labels on the target domain as well as domain labels in the feature extractor, and we demonstrate the effectiveness of our method on the challenging NIST SRE16 and SRE18 benchmarks.
   author = {A. Johan Rohdin and Themos Stafylakis and Anna
	Silnova and Hossein Zeinali and Luk{\'{a}}{\v{s}}
	Burget and Old{\v{r}}ich Plchot},
   title = {Speaker Verification Using End-To-End Adversarial
	Language Adaptation},
   pages = {6006--6010},
   booktitle = {Proceedings of ICASSP 2019},
   year = 2019,
   location = {Brighton, GB},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-5386-4658-8},
   language = {english},
   url = {}

Your IPv4 address:
Switch to https