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

This paper addresses the problem of automatic speech recognition (ASR) of atarget speaker in background speech. The novelty of our approach is that wefocus on a wakeup keyword, which is usually used for activating ASR systemslike smart speakers. The proposed method firstly utilizes a DNN-based maskestimator to separate the mixture signal into the keyword signal uttered by thetarget speaker and the remaining background speech. Then the separated signalsare used for calculating a beamforming filter to enhance the subsequentutterances from the target speaker. Experimental evaluations show that thetrained DNN-based mask can selectively separate the keyword and backgroundspeech from the mixture signal. The effectiveness of the proposed method isalso verified with Japanese ASR experiments, and we confirm that the charactererror rates are significantly improved by the proposed method for bothsimulated and real recorded test sets.

Speaker Selective Beamformer with Keyword Mask Estimation