Improving End-to-end Contextual Speech Recognition With Fine-grained Contextual Knowledge Selection
2022 · Minglun Han, Linhao Dong, Zhenlin Liang, et al.
Abstract
Nowadays, most methods in end-to-end contextual speech recognition bias the recognition process towards contextual knowledge. Since all-neural contextual biasing methods rely on phrase-level contextual modeling and attention-based relevance modeling, they may encounter confusion between similar context-specific phrases, which hurts predictions at the token level. In this work, we focus on mitigating confusion problems with fine-grained contextual knowledge selection (FineCoS). In FineCoS, we introduce fine-grained knowledge to reduce the uncertainty of token predictions. Specifically, we first apply phrase selection to narrow the range of phrase candidates, and then conduct token attention on the tokens in the selected phrase candidates. Moreover, we re-normalize the attention weights of most relevant phrases in inference to obtain more focused phrase-level contextual representations, and inject position information to better discriminate phrases or tokens. On LibriSpeech and an in-hou
Authors
(none)
Tags
Stats
Related papers
- Contextualized End-to-end Speech Recognition With Contextual Phrase Prediction Network (2023)10.48
- Improving Neural Biasing For Contextual Speech Recognition By Early Context Injection And Text Perturbation (2024)8.09
- Contextualized End-to-end Automatic Speech Recognition With Intermediate Biasing Loss (2024)5.84
- Robust Acoustic And Semantic Contextual Biasing In Neural Transducers For Speech Recognition (2023)8.60
- Contextualized Streaming End-to-end Speech Recognition With Trie-based Deep Biasing And Shallow Fusion (2021)13.44
- Locality Enhanced Dynamic Biasing And Sampling Strategies For Contextual ASR (2024)0.00
- Towards Contextual Spelling Correction For Customization Of End-to-end Speech Recognition Systems (2022)9.92
- Cif-based Collaborative Decoding For End-to-end Contextual Speech Recognition (2020)9.76