Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environments
This work addresses speech recognition accuracy in challenging acoustic conditions, but it is incremental as it builds on existing DNN methods with a new feature.
The paper tackled the problem of speech recognition in noisy and reverberant environments by proposing a spatial diffuseness feature for DNN-based models, resulting in a reduced word error rate on the REVERB challenge corpus compared to baseline features.
We propose a spatial diffuseness feature for deep neural network (DNN)-based automatic speech recognition to improve recognition accuracy in reverberant and noisy environments. The feature is computed in real-time from multiple microphone signals without requiring knowledge or estimation of the direction of arrival, and represents the relative amount of diffuse noise in each time and frequency bin. It is shown that using the diffuseness feature as an additional input to a DNN-based acoustic model leads to a reduced word error rate for the REVERB challenge corpus, both compared to logmelspec features extracted from noisy signals, and features enhanced by spectral subtraction.