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

Monaural speech enhancement (SE) is an ill-posed problem due to theirreversible degradation process. Recent methods to achieve SE tasks relysolely on positive information, e.g., ground-truth speech and speech-relevantfeatures. Different from the above, we observe that the negative information,such as original speech mixture and speech-irrelevant features, are valuable toguide the SE model training procedure. In this study, we propose a SE modelthat integrates both speech positive and negative information for improving SEperformance by adopting contrastive learning, in which two innovations haveconsisted. (1) We design a collaboration module (CM), which contains two parts,contrastive attention for separating relevant and irrelevant features viacontrastive learning and interactive attention for establishing the correlationbetween both speech features in a learnable and self-adaptive manner. (2) Wepropose a contrastive regularization (CR) built upon contrastive learning toensure that the estimated speech is pulled closer to the clean speech andpushed far away from the noisy speech in the representation space byintegrating self-supervised models. We term the proposed SE network with CM andCR as CMCR-Net. Experimental results demonstrate that our CMCR-Net achievescomparable and superior performance to recent approaches.

All Information is Necessary: Integrating Speech Positive and Negative Information by Contrastive Learning for Speech Enhancement