Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910973641621504 |
|---|---|
| author | Lin, Zhennan Huang, Kaixun Ren, Wei Yang, Linju Xie, Lei |
| author_facet | Lin, Zhennan Huang, Kaixun Ren, Wei Yang, Linju Xie, Lei |
| contents | Deep biasing improves automatic speech recognition (ASR) performance by incorporating contextual phrases. However, most existing methods enhance subwords in a contextual phrase as independent units, potentially compromising contextual phrase integrity, leading to accuracy reduction. In this paper, we propose an encoder-based phrase-level contextualized ASR method that leverages dynamic vocabulary prediction and activation. We introduce architectural optimizations and integrate a bias loss to extend phrase-level predictions based on frame-level outputs. We also introduce a confidence-activated decoding method that ensures the complete output of contextual phrases while suppressing incorrect bias. Experiments on Librispeech and Wenetspeech datasets demonstrate that our approach achieves relative WER reductions of 28.31% and 23.49% compared to baseline, with the WER on contextual phrases decreasing relatively by 72.04% and 75.69%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23077 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation Lin, Zhennan Huang, Kaixun Ren, Wei Yang, Linju Xie, Lei Sound Computation and Language Audio and Speech Processing Deep biasing improves automatic speech recognition (ASR) performance by incorporating contextual phrases. However, most existing methods enhance subwords in a contextual phrase as independent units, potentially compromising contextual phrase integrity, leading to accuracy reduction. In this paper, we propose an encoder-based phrase-level contextualized ASR method that leverages dynamic vocabulary prediction and activation. We introduce architectural optimizations and integrate a bias loss to extend phrase-level predictions based on frame-level outputs. We also introduce a confidence-activated decoding method that ensures the complete output of contextual phrases while suppressing incorrect bias. Experiments on Librispeech and Wenetspeech datasets demonstrate that our approach achieves relative WER reductions of 28.31% and 23.49% compared to baseline, with the WER on contextual phrases decreasing relatively by 72.04% and 75.69%. |
| title | Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation |
| topic | Sound Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.23077 |