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 investigates the possibility of extracting a target sentence frommulti-talker speech using only a keyword as input. For example, in socialsecurity applications, the keyword might be "help", and the goal is to identifywhat the person who called for help is articulating while ignoring otherspeakers. To address this problem, we propose using the Transformerarchitecture to embed both the keyword and the speech utterance and then relyon the cross-attention mechanism to select the correct content from theconcatenated or overlapping speech. Experimental results on Librispeechdemonstrate that our proposed method can effectively extract target sentencesfrom very noisy and mixed speech (SNR=-3dB), achieving a phone error rate (PER)of 26\%, compared to the baseline system's PER of 96%.

A Glance is Enough: Extract Target Sentence By Looking at A keyword