June 1, 2013
Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux and John R. Hershey
The results of the 2nd 'CHiME' Speech Separation and Recognition Challenge are out! The team formed by MELCO researcher Yuuki Tachioka and MERL Speech & Audio team researchers Shinji Watanabe, Jonathan Le Roux and John Hershey obtained the best results in the continuous speech recognition task (Track 2). This very challenging task consisted in recognizing speech corrupted by highly non-stationary noises recorded in a real living room. Our proposal, which also included a simple yet extremely efficient denoising front-end, focused on investigating and developing state-of-the-art automatic speech recognition back-end techniques: feature transformation methods, as well as discriminative training methods for acoustic and language modeling. Our system significantly outperformed other participants. Our code has since been released as an improved baseline for the community to use.
"Discriminative Methods for Noise Robust Speech Recognition: A CHiME Challenge Benchmark"
International Workshop on Machine Listening in Multisource Environments (CHiME)