Publication detail

Speaker activity driven neural speech extraction

DELCROIX, M. ŽMOLÍKOVÁ, K. OCHIAI, T. KINOSHITA, K. NAKATANI, T.

Original Title

Speaker activity driven neural speech extraction

Type

conference paper

Language

English

Original Abstract

Target speech extraction, which extracts the speech of a targetspeaker in a mixture given auxiliary speaker clues, has recentlyreceived increased interest. Various clues have been investigatedsuch as pre-recorded enrollment utterances, direction information,or video of the target speaker. In this paper, we explore the use ofspeaker activity information as an auxiliary clue for single-channelneural network-based speech extraction. We propose a speaker activitydriven speech extraction neural network (ADEnet) and showthat it can achieve performance levels competitive with enrollmentbasedapproaches, without the need for pre-recordings. We furtherdemonstrate the potential of the proposed approach for processingmeeting-like recordings, where speaker activity obtained from a diarizationsystem is used as a speaker clue for ADEnet. We show thatthis simple yet practical approach can successfully extract speakersafter diarization, which leads to improved ASR performancewhen using a single microphone, especially in high overlappingconditions, with relative word error rate reduction of up to 25 %.

Keywords

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

Authors

DELCROIX, M.; ŽMOLÍKOVÁ, K.; OCHIAI, T.; KINOSHITA, K.; NAKATANI, T.

Released

6. 6. 2021

Publisher

IEEE Signal Processing Society

Location

Toronto

ISBN

978-1-7281-7605-5

Book

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Pages from

6099

Pages to

6103

Pages count

5

URL

https://www.fit.vut.cz/research/publication/12479/

BibTex

@inproceedings{BUT171749,
  author="DELCROIX, M. and ŽMOLÍKOVÁ, K. and OCHIAI, T. and KINOSHITA, K. and NAKATANI, T.",
  title="Speaker activity driven neural speech extraction",
  booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
  year="2021",
  pages="6099--6103",
  publisher="IEEE Signal Processing Society",
  address="Toronto",
  doi="10.1109/ICASSP39728.2021.9414998",
  isbn="978-1-7281-7605-5",
  url="https://www.fit.vut.cz/research/publication/12479/"
}

Documents

delcroix_icassp2021_09414998.pdf