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 been successfully applied to tasks likeimage classification and language modeling for finding efficienthigh-performance network architectures. In ASR field especially end-to-end ASR,the related research is still in its infancy. In this work, we focus onapplying NAS on the most popular manually designed model: Conformer, and thenpropose an efficient ASR model searching method that benefits from the naturaladvantage of differentiable architecture search (Darts) in reducingcomputational overheads. We fuse Darts mutator and Conformer blocks to form acomplete search space, within which a modified architecture calledDarts-Conformer cell is found automatically. The entire searching process onAISHELL-1 dataset costs only 0.7 GPU days. Replacing the Conformer encoder bystacking searched cell, we get an end-to-end ASR model (named asDarts-Conformner) that outperforms the Conformer baseline by 4.7\% on theopen-source AISHELL-1 dataset. Besides, we verify the transferability of thearchitecture searched on a small dataset to a larger 2k-hour dataset. To thebest of our knowledge, this is the first successful attempt to applygradient-based architecture search in the attention-based encoder-decoder ASRmodel.

Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR