2021/05/08 by Liqiang He, He, Liqiang, Shulin Feng +5
Computer Science · #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 #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2105.03643
openalex publication_date 2021/05/08 · openalex created_date 2021/05/24 · openalex updated_date 2026/07/28
Neural architecture search (NAS) has attracted much attention and has been explored for automatic speech recognition (ASR). In this work, we focus on streaming ASR scenarios and propose the latency-controlled NAS for acoustic modeling. First, based on the vanilla neural architecture, normal cells are altered to causal cells to control the total latency of the architecture. Second, a revised operation space with a smaller receptive field is proposed to generate the final architecture with low latency. Extensive experiments show that: 1) Based on the proposed neural architecture, the neural networks with a medium latency of 550ms (millisecond) and a low latency of 190ms can be learned in the vanilla and revised operation space respectively. 2) For the low latency setting, the evaluation network can achieve more than 19% (average on the four test sets) relative improvements compared with the hybrid CLDNN baseline, on a 10k-hour large-scale dataset.