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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Recently, excellent progress has been made in speech recognition. However,pure data-driven approaches have struggled to solve the problem indomain-mismatch and long-tailed data. Considering that knowledge-drivenapproaches can help data-driven approaches alleviate their flaws, we introducesememe-based semantic knowledge information to speech recognition (SememeASR).Sememe, according to the linguistic definition, is the minimum semantic unit ina language and is able to represent the implicit semantic information behindeach word very well. Our experiments show that the introduction of sememeinformation can improve the effectiveness of speech recognition. In addition,our further experiments show that sememe knowledge can improve the model'srecognition of long-tailed data and enhance the model's domain generalizationability.

SememeASR: Boosting Performance of End-to-End Speech Recognition against Domain and Long-Tailed Data Shift with Sememe Semantic Knowledge