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

Streaming end-to-end multi-talker speech recognition aims at transcribing theoverlapped speech from conversations or meetings with an all-neural model in astreaming fashion, which is fundamentally different from a modular-basedapproach that usually cascades the speech separation and the speech recognitionmodels trained independently. Previously, we proposed the Streaming Unmixingand Recognition Transducer (SURT) model based on recurrent neural networktransducer (RNN-T) for this problem and presented promising results. However,for real applications, the speech recognition system is also required todetermine the timestamp when a speaker finishes speaking for prompt systemresponse. This problem, known as endpoint (EP) detection, has not been studiedpreviously for multi-talker end-to-end models. In this work, we address the EPdetection problem in the SURT framework by introducing an end-of-sentence tokenas an output unit, following the practice of single-talker end-to-end models.Furthermore, we also present a latency penalty approach that can significantlycut down the EP detection latency. Our experimental results based on the2-speaker LibrispeechMix dataset show that the SURT model can achieve promisingEP detection without significantly degradation of the recognition accuracy.

Endpoint Detection for Streaming End-to-End Multi-talker ASR