The second 'chime' speech separation and recognition challenge

Datasets, tasks and baselines

Emmanuel Vincent, Jon Barker, Shinji Watanabe, Jonathan Le Roux, Francesco Nesta, Marco Matassoni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

128 Citations (Scopus)

Abstract

Distant-microphone automatic speech recognition (ASR) remains a challenging goal in everyday environments involving multiple background sources and reverberation. This paper is intended to be a reference on the 2nd 'CHiME' Challenge, an initiative designed to analyze and evaluate the performance of ASR systems in a real-world domestic environment. Two separate tracks have been proposed: a small-vocabulary task with small speaker movements and a medium-vocabulary task without speaker movements. We discuss the rationale for the challenge and provide a detailed description of the datasets, tasks and baseline performance results for each track.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages126-130
Number of pages5
DOIs
Publication statusPublished - 2013 Oct 18
Externally publishedYes
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC
Duration: 2013 May 262013 May 31

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CityVancouver, BC
Period13/5/2613/5/31

Fingerprint

Speech recognition
Reverberation
Microphones

Keywords

  • 'CHiME' Challenge
  • Noise-robust ASR

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Vincent, E., Barker, J., Watanabe, S., Le Roux, J., Nesta, F., & Matassoni, M. (2013). The second 'chime' speech separation and recognition challenge: Datasets, tasks and baselines. In 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings (pp. 126-130). [6637622] https://doi.org/10.1109/ICASSP.2013.6637622

The second 'chime' speech separation and recognition challenge : Datasets, tasks and baselines. / Vincent, Emmanuel; Barker, Jon; Watanabe, Shinji; Le Roux, Jonathan; Nesta, Francesco; Matassoni, Marco.

2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. 2013. p. 126-130 6637622.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vincent, E, Barker, J, Watanabe, S, Le Roux, J, Nesta, F & Matassoni, M 2013, The second 'chime' speech separation and recognition challenge: Datasets, tasks and baselines. in 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings., 6637622, pp. 126-130, 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, Vancouver, BC, 13/5/26. https://doi.org/10.1109/ICASSP.2013.6637622
Vincent E, Barker J, Watanabe S, Le Roux J, Nesta F, Matassoni M. The second 'chime' speech separation and recognition challenge: Datasets, tasks and baselines. In 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. 2013. p. 126-130. 6637622 https://doi.org/10.1109/ICASSP.2013.6637622
Vincent, Emmanuel ; Barker, Jon ; Watanabe, Shinji ; Le Roux, Jonathan ; Nesta, Francesco ; Matassoni, Marco. / The second 'chime' speech separation and recognition challenge : Datasets, tasks and baselines. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. 2013. pp. 126-130
@inproceedings{897a2ee65eda47ec8a2d5aba946afd12,
title = "The second 'chime' speech separation and recognition challenge: Datasets, tasks and baselines",
abstract = "Distant-microphone automatic speech recognition (ASR) remains a challenging goal in everyday environments involving multiple background sources and reverberation. This paper is intended to be a reference on the 2nd 'CHiME' Challenge, an initiative designed to analyze and evaluate the performance of ASR systems in a real-world domestic environment. Two separate tracks have been proposed: a small-vocabulary task with small speaker movements and a medium-vocabulary task without speaker movements. We discuss the rationale for the challenge and provide a detailed description of the datasets, tasks and baseline performance results for each track.",
keywords = "'CHiME' Challenge, Noise-robust ASR",
author = "Emmanuel Vincent and Jon Barker and Shinji Watanabe and {Le Roux}, Jonathan and Francesco Nesta and Marco Matassoni",
year = "2013",
month = "10",
day = "18",
doi = "10.1109/ICASSP.2013.6637622",
language = "English",
isbn = "9781479903566",
pages = "126--130",
booktitle = "2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings",

}

TY - GEN

T1 - The second 'chime' speech separation and recognition challenge

T2 - Datasets, tasks and baselines

AU - Vincent, Emmanuel

AU - Barker, Jon

AU - Watanabe, Shinji

AU - Le Roux, Jonathan

AU - Nesta, Francesco

AU - Matassoni, Marco

PY - 2013/10/18

Y1 - 2013/10/18

N2 - Distant-microphone automatic speech recognition (ASR) remains a challenging goal in everyday environments involving multiple background sources and reverberation. This paper is intended to be a reference on the 2nd 'CHiME' Challenge, an initiative designed to analyze and evaluate the performance of ASR systems in a real-world domestic environment. Two separate tracks have been proposed: a small-vocabulary task with small speaker movements and a medium-vocabulary task without speaker movements. We discuss the rationale for the challenge and provide a detailed description of the datasets, tasks and baseline performance results for each track.

AB - Distant-microphone automatic speech recognition (ASR) remains a challenging goal in everyday environments involving multiple background sources and reverberation. This paper is intended to be a reference on the 2nd 'CHiME' Challenge, an initiative designed to analyze and evaluate the performance of ASR systems in a real-world domestic environment. Two separate tracks have been proposed: a small-vocabulary task with small speaker movements and a medium-vocabulary task without speaker movements. We discuss the rationale for the challenge and provide a detailed description of the datasets, tasks and baseline performance results for each track.

KW - 'CHiME' Challenge

KW - Noise-robust ASR

UR - http://www.scopus.com/inward/record.url?scp=84890541701&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890541701&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2013.6637622

DO - 10.1109/ICASSP.2013.6637622

M3 - Conference contribution

SN - 9781479903566

SP - 126

EP - 130

BT - 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings

ER -