Thumbnail
Access Restriction
Open

Author Vincent, Emmanuel ♦ Barker, Jon ♦ Watanabe, Shinji ♦ Roux, Jonathan Le ♦ Nesta, Francesco ♦ Matassoni, Marco
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Description Distant-microphone automatic speech recognition (ASR) re-mains a challenging goal in everyday environments involving multiple background sources and reverberation. This paper reports on the results of the 2nd ‘CHiME ’ Challenge, an ini-tiative designed to analyse and evaluate the performance of ASR systems in a real-world domestic environment. We dis-cuss 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 chal-lenge findings including novel results produced by challenge system combination. Possible directions for future challenges are discussed. Index Terms — Noise-robust ASR, ‘CHiME ’ Challenge 1.
in Proc. ICASSP 2013
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2013-01-01