Publication detail

Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model

KOCOUR, M. ŽMOLÍKOVÁ, K. ONDEL YANG, L. ŠVEC, J. DELCROIX, M. OCHIAI, T. BURGET, L. ČERNOCKÝ, J.

Original Title

Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model

Type

conference paper

Language

English

Original Abstract

In typical multi-talker speech recognition systems, a neural network-based acoustic model predicts senone state posteriors for each speaker. These are later used by a single-talker decoder which is applied on each speaker-specific output stream separately. In this work, we argue that such a scheme is sub-optimal and propose a principled solution that decodes all speakers jointly. We modify the acoustic model to predict joint state posteriors for all speakers, enabling the network to express uncertainty about the attribution of parts of the speech signal to the speakers. We employ a joint decoder that can make use of this uncertainty together with higher-level language information. For this, we revisit decoding algorithms used in factorial generative models in early multi-talker speech recognition systems. In contrast with these early works, we replace the GMM acoustic model with DNN, which provides greater modeling power and simplifies part of the inference. We demonstrate the advantage of joint decoding in proof of concept experiments on a mixed-TIDIGITS dataset.

Keywords

Multi-talker speech recognition, Permutation invariant training, Factorial Hidden Markov models

Authors

KOCOUR, M.; ŽMOLÍKOVÁ, K.; ONDEL YANG, L.; ŠVEC, J.; DELCROIX, M.; OCHIAI, T.; BURGET, L.; ČERNOCKÝ, J.

Released

18. 9. 2022

Publisher

International Speech Communication Association

Location

Incheon

ISBN

1990-9772

Periodical

Proceedings of Interspeech

Number

9

State

French Republic

Pages from

4955

Pages to

4959

Pages count

5

URL

https://www.isca-speech.org/archive/pdfs/interspeech_2022/kocour22_interspeech.pdf

BibTex

@inproceedings{BUT179827,
  author="KOCOUR, M. and ŽMOLÍKOVÁ, K. and ONDEL YANG, L. and ŠVEC, J. and DELCROIX, M. and OCHIAI, T. and BURGET, L. and ČERNOCKÝ, J.",
  title="Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model",
  booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
  year="2022",
  journal="Proceedings of Interspeech",
  number="9",
  pages="4955--4959",
  publisher="International Speech Communication Association",
  address="Incheon",
  doi="10.21437/Interspeech.2022-10406",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/pdfs/interspeech_2022/kocour22_interspeech.pdf"
}