Abstract:

The recently introduced REVERB challenge includes a reverberant speech recognition task. We focus on state-of-the-art ASR techniques such as discriminative training and various feature trans- formations including Gaussian mixture model, sub-space Gaussian mixture model, and deep neural networks, in addition to the pro- posed single channel dereverberation method with reverberation time estimation and multi-channel beamforming that enhances direct sound compared with the reflected sound. In addition, because the best performing system is different from environment to environment, we perform a system combination approach using different feature and different types of systems to handle these various environments in the challenge. Moreover, we use our discriminative training technique for system combination that improves system combination by making systems complementary. Experiments show the effectiveness of these approaches, reaching 6.76% and 18.60% word error rate on the REVERB simulated and real test sets, which are 68.8% and 61.5% relative improvements over the baseline.