English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Neural architecture search (NAS) has attracted much attention and has beenexplored for automatic speech recognition (ASR). In this work, we focus onstreaming ASR scenarios and propose the latency-controlled NAS for acousticmodeling. First, based on the vanilla neural architecture, normal cells arealtered to causal cells to control the total latency of the architecture.Second, a revised operation space with a smaller receptive field is proposed togenerate the final architecture with low latency. Extensive experiments showthat: 1) Based on the proposed neural architecture, the neural networks with amedium latency of 550ms (millisecond) and a low latency of 190ms can be learnedin the vanilla and revised operation space respectively. 2) For the low latencysetting, the evaluation network can achieve more than 19\% (average on the fourtest sets) relative improvements compared with the hybrid CLDNN baseline, on a10k-hour large-scale dataset.

Latency-Controlled Neural Architecture Search for Streaming Speech Recognition