2019/11/05 by Weipeng He, Lu Lu, He, Weipeng +9
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1911.02115
To be presented at ICASSP 2020
openalex publication_date 2019/11/05 · openalex created_date 2019/11/22 · arxiv created 2020/03/09 · arxiv updated 2020/03/10 · openalex updated_date 2026/07/28
In this paper, we introduce spatial attention for refining the information in multi-direction neural beamformer for far-field automatic speech recognition. Previous approaches of neural beamformers with multiple look directions, such as the factored complex linear projection, have shown promising results. However, the features extracted by such methods contain redundant information, as only the direction of the target speech is relevant. We propose using a spatial attention subnet to weigh the features from different directions, so that the subsequent acoustic model could focus on the most relevant features for the speech recognition. Our experimental results show that spatial attention achieves up to 9% relative word error rate improvement over methods without the attention.