Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-field Speech Recognition
This work addresses speech recognition in noisy, far-field environments for applications like voice assistants, presenting an incremental improvement over existing beamformer methods.
The paper tackled the problem of multichannel far-field speech recognition by proposing a self-attention channel combinator frontend, which achieved a 9.3% word error rate reduction compared to a state-of-the-art fixed beamformer-based frontend when jointly optimized with an end-to-end ASR backend.
When a sufficiently large far-field training data is presented, jointly optimizing a multichannel frontend and an end-to-end (E2E) Automatic Speech Recognition (ASR) backend shows promising results. Recent literature has shown traditional beamformer designs, such as MVDR (Minimum Variance Distortionless Response) or fixed beamformers can be successfully integrated as the frontend into an E2E ASR system with learnable parameters. In this work, we propose the self-attention channel combinator (SACC) ASR frontend, which leverages the self-attention mechanism to combine multichannel audio signals in the magnitude spectral domain. Experiments conducted on a multichannel playback test data shows that the SACC achieved a 9.3% WERR compared to a state-of-the-art fixed beamformer-based frontend, both jointly optimized with a ContextNet-based ASR backend. We also demonstrate the connection between the SACC and the traditional beamformers, and analyze the intermediate outputs of the SACC.