On combining features for single-channel robust speech recognition in reverberant environments
This work addresses robust speech recognition for applications in noisy, real-world settings, but it is incremental as it builds on existing combination methods.
This paper tackled the problem of improving speech recognition accuracy in highly-reverberant environments by combining complementary parallel systems, achieving word error rate (WER) improvements of 7% to 18% in real-room recordings.
This paper addresses the combination of complementary parallel speech recognition systems to reduce the error rate of speech recognition systems operating in real highly-reverberant environments. First, the testing environment consists of recordings of speech in a calibrated real room with reverberation times from 0.47 to 1.77 seconds and speaker-to-microphone distances of 0.16 to 2.56 meters. We combined systems both at the level of the DNN outputs and at the level of the final ASR outputs. Second, recognition experiments with the reverb challenge are also reported. The results presented here show that the combination of features can lead to WER improvements between 7% and 18% with speech recorded in real reverberant environments. Also, the combination at DNN-output level is much more effective than at the system-output level. However, cascading both schemes can still lead to smaller reductions in WER.