Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-field Speech Recognition

Autor:	Gong, Rong, Quillen, Carl, Sharma, Dushyant, Goderre, Andrew, Laínez, José, Milanović, Ljubomir
Rok vydání:	2021
Předmět:	Computer Science - Sound Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Machine Learning Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	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. Comment: In Proceedings of Interspeech 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2109.04783 Zobrazit plný text záznamu View this record from Arxiv