Papers with post-processing of Chinese speech recognition

1 papers
Correcting Pronoun Homophones with Subtle Semantics in Chinese Speech Recognition (2024.lrec-main)

Copied to clipboard

Challenge: Chinese speech recognition is becoming prevalent due to the similar semantic context of the entities and the overlap of Chinese pronunciation.
Approach: They propose three models to address common confusion issues in Chinese speech recognition . they implement a language model, a LSTM model with semantic features and a rule-based assisted Ngram model .
Outcome: The proposed models achieve highest recognition rate for “T” correction with improvements from 70% in the popular voice input methods up to 90%.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations