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

Previous studies have confirmed that by augmenting acoustic features with theplace/manner of articulatory features, the speech enhancement (SE) process canbe guided to consider the broad phonetic properties of the input speech whenperforming enhancement to attain performance improvements. In this paper, weexplore the contextual information of articulatory attributes as additionalinformation to further benefit SE. More specifically, we propose to improve theSE performance by leveraging losses from an end-to-end automatic speechrecognition (E2E-ASR) model that predicts the sequence of broad phoneticclasses (BPCs). We also developed multi-objective training with ASR andperceptual losses to train the SE system based on a BPC-based E2E-ASR.Experimental results from speech denoising, speech dereverberation, andimpaired speech enhancement tasks confirmed that contextual BPC informationimproves SE performance. Moreover, the SE model trained with the BPC-basedE2E-ASR outperforms that with the phoneme-based E2E-ASR. The results suggestthat objectives with misclassification of phonemes by the ASR system may leadto imperfect feedback, and BPC could be a potentially better choice. Finally,it is noted that combining the most-confusable phonetic targets into the sameBPC when calculating the additional objective can effectively improve the SEperformance.

Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information