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

Although deep-learning-based methods have markedly improved the performanceof speech separation over the past few years, it remains an open question howto integrate multi-channel signals for speech separation. We propose twomethods, namely, early-fusion and late-fusion methods, to integratemulti-channel information based on the time-domain audio separation network,which has been proven effective in single-channel speech separation. We alsopropose channel-sequential-transfer learning, which is a transfer learningframework that applies the parameters trained for a lower-channel network asthe initial values of a higher-channel network. For fair comparison, weevaluated our proposed methods using a spatialized version of the wsj0-2mixdataset, which is open-sourced. It was found that our proposed methods canoutperform multi-channel deep clustering and improve the performanceproportionally to the number of microphones. It was also proven that theperformance of the late-fusion method is consistently higher than that of thesingle-channel method regardless of the angle difference between speakers.

Efficient Integration of Multi-channel Information for Speaker-independent Speech Separation