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

Speech enhancement (SE) is proved effective in reducing noise from noisyspeech signals for downstream automatic speech recognition (ASR), wheremulti-task learning strategy is employed to jointly optimize these two tasks.However, the enhanced speech learned by SE objective may not always yield goodASR results. From the optimization view, there sometimes exists interferencebetween the gradients of SE and ASR tasks, which could hinder the multi-tasklearning and finally lead to sub-optimal ASR performance. In this paper, wepropose a simple yet effective approach called gradient remedy (GR) to solveinterference between task gradients in noise-robust speech recognition, fromperspectives of both angle and magnitude. Specifically, we first project the SEtask's gradient onto a dynamic surface that is at acute angle to ASR gradient,in order to remove the conflict between them and assist in ASR optimization.Furthermore, we adaptively rescale the magnitude of two gradients to preventthe dominant ASR task from being misled by SE gradient. Experimental resultsshow that the proposed approach well resolves the gradient interference andachieves relative word error rate (WER) reductions of 9.3% and 11.1% overmulti-task learning baseline, on RATS and CHiME-4 datasets, respectively. Ourcode is available at GitHub.

Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition