SememeASR: Boosting Performance of End-to-End Speech Recognition against Domain and Long-Tailed Data Shift with Sememe Semantic Knowledge
This addresses domain and long-tailed data issues in speech recognition, but it is incremental as it builds on existing knowledge-driven approaches.
The paper tackled the problem of domain-mismatch and long-tailed data in end-to-end speech recognition by introducing sememe-based semantic knowledge, resulting in improved effectiveness, better recognition of long-tailed data, and enhanced domain generalization ability.
Recently, excellent progress has been made in speech recognition. However, pure data-driven approaches have struggled to solve the problem in domain-mismatch and long-tailed data. Considering that knowledge-driven approaches can help data-driven approaches alleviate their flaws, we introduce sememe-based semantic knowledge information to speech recognition (SememeASR). Sememe, according to the linguistic definition, is the minimum semantic unit in a language and is able to represent the implicit semantic information behind each word very well. Our experiments show that the introduction of sememe information can improve the effectiveness of speech recognition. In addition, our further experiments show that sememe knowledge can improve the model's recognition of long-tailed data and enhance the model's domain generalization ability.