Publication detail

Multi-Channel Speech Separation with Cross-Attention and Beamforming

MOŠNER, L. PLCHOT, O. PENG, J. BURGET, L. ČERNOCKÝ, J.

Original Title

Multi-Channel Speech Separation with Cross-Attention and Beamforming

Type

conference paper

Language

English

Original Abstract

Originally, single-channel source separation gained more research interest. It resulted in immense progress. Multichannel (MC) separation comes with new challenges posed by adverse indoor conditions making it an important field of study. We seek to combine promising ideas from the two worlds. First, we build MC models by extending current single-channel time-domain separators relying on their strength. Our approach allows reusing pre-trained models by inserting designed lightweight reference channel attention (RCA) combiner, the only trained module. It comprises two blocks: the former allows attending to different parts of other channels w.r.t. the reference one, and the latter provides an attention-based combination of channels. Second, like many successful MC models, our system incorporates beamforming and allows for the fusion of the network and beamformer outputs. We compare our approach with the SOTA models on the SMS-WSJ dataset and show better or similar performance.

Keywords

multi-channel source separation, cross-channel attention, beamforming

Authors

MOŠNER, L.; PLCHOT, O.; PENG, J.; BURGET, L.; ČERNOCKÝ, J.

Released

20. 8. 2023

Publisher

International Speech Communication Association

Location

Dublin

ISBN

1990-9772

Periodical

Proceedings of Interspeech

Year of study

2023

Number

08

State

French Republic

Pages from

1693

Pages to

1697

Pages count

5

URL

https://www.isca-speech.org/archive/interspeech_2023/mosner23_interspeech.html

BibTex

@inproceedings{BUT185571,
  author="Ladislav {Mošner} and Oldřich {Plchot} and Junyi {Peng} and Lukáš {Burget} and Jan {Černocký}",
  title="Multi-Channel Speech Separation with Cross-Attention and Beamforming",
  booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
  year="2023",
  journal="Proceedings of Interspeech",
  volume="2023",
  number="08",
  pages="1693--1697",
  publisher="International Speech Communication Association",
  address="Dublin",
  doi="10.21437/Interspeech.2023-2537",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/interspeech_2023/mosner23_interspeech.html"
}

Documents

mosner23_interspeech2023_multi-channel.pdf