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

Recently, the research on ad-hoc microphone arrays with deep learning hasdrawn much attention, especially in speech enhancement and separation. Becausean ad-hoc microphone array may cover such a large area that multiple speakersmay locate far apart and talk independently, target-dependent speechseparation, which aims to extract a target speaker from a mixed speech, isimportant for extracting and tracing a specific speaker in the ad-hoc array.However, this technique has not been explored yet. In this paper, we proposedeep ad-hoc beamforming based on speaker extraction, which is to our knowledgethe first work for target-dependent speech separation based on ad-hocmicrophone arrays and deep learning. The algorithm contains three components.First, we propose a supervised channel selection framework based on speakerextraction, where the estimated utterance-level SNRs of the target speech areused as the basis for the channel selection. Second, we apply the selectedchannels to a deep learning based MVDR algorithm, where a single-channelspeaker extraction algorithm is applied to each selected channel for estimatingthe mask of the target speech. We conducted an extensive experiment on aWSJ0-adhoc corpus. Experimental results demonstrate the effectiveness of theproposed method.

Deep Ad-hoc Beamforming Based on Speaker Extraction for Target-Dependent Speech Separation