Publication Details

Speaker activity driven neural speech extraction

DELCROIX Marc, ŽMOLÍKOVÁ Kateřina, OCHIAI Tsubasa, KINOSHITA Keisuke and NAKATANI Tomohiro. Speaker activity driven neural speech extraction. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Toronto: IEEE Signal Processing Society, 2021, pp. 6099-6103. ISBN 978-1-7281-7605-5.
Czech title
Neurální extrakce řeči řízená aktivitou řečníka
Type
conference paper
Language
english
Authors
Delcroix Marc (NTT)
Žmolíková Kateřina, Ing., Ph.D. (DCGM FIT BUT)
Ochiai Tsubasa (NTT)
Kinoshita Keisuke (NTT)
Nakatani Tomohiro (NTT)
URL
Keywords

Speech extraction, Speaker activity, Speech enhancement, Meeting recognition, Neural network

Abstract

Target speech extraction, which extracts the speech of a target speaker in a mixture given auxiliary speaker clues, has recently received increased interest. Various clues have been investigated such as pre-recorded enrollment utterances, direction information, or video of the target speaker. In this paper, we explore the use of speaker activity information as an auxiliary clue for single-channel neural network-based speech extraction. We propose a speaker activity driven speech extraction neural network (ADEnet) and show that it can achieve performance levels competitive with enrollmentbased approaches, without the need for pre-recordings. We further demonstrate the potential of the proposed approach for processing meeting-like recordings, where speaker activity obtained from a diarization system is used as a speaker clue for ADEnet. We show that this simple yet practical approach can successfully extract speakers after diarization, which leads to improved ASR performance when using a single microphone, especially in high overlapping conditions, with relative word error rate reduction of up to 25 %.

Published
2021
Pages
6099-6103
Proceedings
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Conference
2021 IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, CA
ISBN
978-1-7281-7605-5
Publisher
IEEE Signal Processing Society
Place
Toronto, CA
DOI
UT WoS
000704288406074
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12479,
   author = "Marc Delcroix and Kate\v{r}ina \v{Z}mol\'{i}kov\'{a} and Tsubasa Ochiai and Keisuke Kinoshita and Tomohiro Nakatani",
   title = "Speaker activity driven neural speech extraction",
   pages = "6099--6103",
   booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
   year = 2021,
   location = "Toronto, CA",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-7281-7605-5",
   doi = "10.1109/ICASSP39728.2021.9414998",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12479"
}
Back to top