Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
STAFYLAKIS, T. ROHDIN, J. PLCHOT, O. MIZERA, P. BURGET, L.
Originální název
Self-supervised speaker embeddings
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers. In this paper, we explore an alternative training strategy to enable the use of unlabelled utterances in training. We propose to train speaker embedding extractors via reconstructing the frames of a target speech segment, given the inferred embedding of another speech segment of the same utterance. We do this by attaching to the standard speaker embedding extractor a decoder network, which we feed not merely with the speaker embedding, but also with the estimated phone sequence of the target frame sequence. The reconstruction loss can be used either as a single objective, or be combined with the standard speaker classification loss. In the latter case, it acts as a regularizer, encouraging generalizability to speakers unseen during training. In all cases, the proposed architectures are trained from scratch and in an endto- end fashion. We demonstrate the benefits from the proposed approach on the VoxCeleb and Speakers in the Wild Databases, and we report notable improvements over the baseline.
Klíčová slova
speaker recognition, self-supervised learning, deep learning
Autoři
STAFYLAKIS, T.; ROHDIN, J.; PLCHOT, O.; MIZERA, P.; BURGET, L.
Vydáno
15. 9. 2019
Nakladatel
International Speech Communication Association
Místo
Graz
ISSN
1990-9772
Periodikum
Proceedings of Interspeech
Ročník
2019
Číslo
9
Stát
Francouzská republika
Strany od
2863
Strany do
2867
Strany počet
5
URL
https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2842.pdf
BibTex
@inproceedings{BUT159999, author="STAFYLAKIS, T. and ROHDIN, J. and PLCHOT, O. and MIZERA, P. and BURGET, L.", title="Self-supervised speaker embeddings", booktitle="Proceedings of Interspeech", year="2019", journal="Proceedings of Interspeech", volume="2019", number="9", pages="2863--2867", publisher="International Speech Communication Association", address="Graz", doi="10.21437/Interspeech.2019-2842", issn="1990-9772", url="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/2842.pdf" }