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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper describes our submission to the Second Clarity EnhancementChallenge (CEC2), which consists of target speech enhancement for hearing-aid(HA) devices in noisy-reverberant environments with multiple interferers suchas music and competing speakers.  Our approach builds upon the powerful iterative neural/beamformingenhancement (iNeuBe) framework introduced in our recent work, and this paperextends it for target speaker extraction. We therefore name the proposedapproach as iNeuBe-X, where the X stands for extraction. To address thechallenges encountered in the CEC2 setting, we introduce four major novelties:  (1) we extend the state-of-the-art TF-GridNet model, originally designed formonaural speaker separation, for multi-channel, causal speech enhancement, andlarge improvements are observed by replacing the TCNDenseNet used in iNeuBewith this new architecture;  (2) we leverage a recent dual window size approach with future-frameprediction to ensure that iNueBe-X satisfies the 5 ms constraint on algorithmiclatency required by CEC2;  (3) we introduce a novel speaker-conditioning branch for TF-GridNet toachieve target speaker extraction;  (4) we propose a fine-tuning step, where we compute an additional loss withrespect to the target speaker signal compensated with the listener audiogram.  Without using external data, on the official development set our best modelreaches a hearing-aid speech perception index (HASPI) score of 0.942 and ascale-invariant signal-to-distortion ratio improvement (SI-SDRi) of 18.8 dB.These results are promising given the fact that the CEC2 data is extremelychallenging (e.g., on the development set the mixture SI-SDR is -12.3 dB). Ademo of our submitted system is available at WAVLab CEC2 demo.

Multi-Channel Target Speaker Extraction with Refinement: The WavLab Submission to the Second Clarity Enhancement Challenge