TR2013-079

The Second 'CHiME' Speech Separation and Recognition Challenge: Datasets, Tasks and Baselines


    •  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", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
      BibTeX TR2013-079 PDF
      • @inproceedings{Vincent2013may,
      • author = {Vincent, E. and Barker, J. and Watanabe, S. and {Le Roux}, J. and Nesta, F. and Matassoni, M.},
      • title = {The Second 'CHiME' Speech Separation and Recognition Challenge: Datasets, Tasks and Baselines},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2013,
      • month = may,
      • url = {https://www.merl.com/publications/TR2013-079}
      • }
  • MERL Contact:
  • Research Areas:

    Artificial Intelligence, Speech & Audio

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.