The Second 'CHiME' Speech Separation and Recognition Challenge: An overview of challenge systems and outcomes

Abstract : Distant-microphone automatic speech recognition (ASR) remains a challenging goal in everyday environments involving multiple background sources and reverberation. This paper reports on the results of the 2nd 'CHiME' Challenge, an initiative designed to analyse and evaluate the performance of ASR systems in a real-world domestic environment. We discuss the rationale for the challenge and provide a summary of the datasets, tasks and baseline systems. The paper overviews the systems that were entered for the two challenge tracks: small-vocabulary with moving talker and medium-vocabulary with stationary talker. We present a summary of the challenge findings including novel results produced by challenge system combination. Possible directions for future challenges are discussed.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/hal-00862750
Contributor : Emmanuel Vincent <>
Submitted on : Tuesday, September 17, 2013 - 2:11:27 PM
Last modification on : Saturday, March 30, 2019 - 1:26:19 AM
Long-term archiving on : Friday, December 20, 2013 - 2:27:40 PM

File

vincent_ASRU13.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00862750, version 1

Collections

Citation

Emmanuel Vincent, Jon Barker, Shinji Watanabe, Jonathan Le Roux, Francesco Nesta, et al.. The Second 'CHiME' Speech Separation and Recognition Challenge: An overview of challenge systems and outcomes. 2013 IEEE Automatic Speech Recognition and Understanding Workshop, Dec 2013, Olomouc, Czech Republic. ⟨hal-00862750⟩

Share

Metrics

Record views

365

Files downloads

580