InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictions
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917700460085248 |
|---|---|
| author | Nakagome, Yu Hentschel, Michael |
| author_facet | Nakagome, Yu Hentschel, Michael |
| contents | Despite recent advances in end-to-end speech recognition methods, their output is biased to the training data's vocabulary, resulting in inaccurate recognition of unknown terms or proper nouns. To improve the recognition accuracy for a given set of such terms, we propose an adaptation parameter-free approach based on Self-conditioned CTC. Our method improves the recognition accuracy of misrecognized target keywords by substituting their intermediate CTC predictions with corrected labels, which are then passed on to the subsequent layers. First, we create pairs of correct labels and recognition error instances for a keyword list using Text-to-Speech and a recognition model. We use these pairs to replace intermediate prediction errors by the labels. Conditioning the subsequent layers of the encoder on the labels, it is possible to acoustically evaluate the target keywords. Experiments conducted in Japanese demonstrated that our method successfully improved the F1 score for unknown words. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14890 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictions Nakagome, Yu Hentschel, Michael Computation and Language Audio and Speech Processing Despite recent advances in end-to-end speech recognition methods, their output is biased to the training data's vocabulary, resulting in inaccurate recognition of unknown terms or proper nouns. To improve the recognition accuracy for a given set of such terms, we propose an adaptation parameter-free approach based on Self-conditioned CTC. Our method improves the recognition accuracy of misrecognized target keywords by substituting their intermediate CTC predictions with corrected labels, which are then passed on to the subsequent layers. First, we create pairs of correct labels and recognition error instances for a keyword list using Text-to-Speech and a recognition model. We use these pairs to replace intermediate prediction errors by the labels. Conditioning the subsequent layers of the encoder on the labels, it is possible to acoustically evaluate the target keywords. Experiments conducted in Japanese demonstrated that our method successfully improved the F1 score for unknown words. |
| title | InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictions |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.14890 |