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

In multi-talker scenarios such as meetings and conversations, speechprocessing systems are usually required to segment the audio and thentranscribe each segmentation. These two stages are addressed separately byspeaker change detection (SCD) and automatic speech recognition (ASR). Mostprevious SCD systems rely solely on speaker information and ignore theimportance of speech content. In this paper, we propose a novel SCD system thatconsiders both cues of speaker difference and speech content. These two cuesare converted into token-level representations by the continuousintegrate-and-fire (CIF) mechanism and then combined for detecting speakerchanges on the token acoustic boundaries. We evaluate the performance of ourapproach on a public real-recorded meeting dataset, AISHELL-4. The experimentresults show that our method outperforms a competitive frame-level baselinesystem by 2.45% equal coverage-purity (ECP). In addition, we demonstrate theimportance of speech content and speaker difference to the SCD task, and theadvantages of conducting SCD on the token acoustic boundaries compared withconducting SCD frame by frame.

Token-level Speaker Change Detection Using Speaker Difference and Speech Content via Continuous Integrate-and-fire