Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.00804 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929654355460096 |
|---|---|
| author | Cheng, Gaofeng Lu, Haitian Yang, Chengxu Wang, Xuyang Li, Ta Yan, Yonghong |
| author_facet | Cheng, Gaofeng Lu, Haitian Yang, Chengxu Wang, Xuyang Li, Ta Yan, Yonghong |
| contents | Effectively distinguishing the pronunciation correlations between different written texts is a significant issue in linguistic acoustics. Traditionally, such pronunciation correlations are obtained through manually designed pronunciation lexicons. In this paper, we propose a data-driven method to automatically acquire these pronunciation correlations, called automatic text pronunciation correlation (ATPC). The supervision required for this method is consistent with the supervision needed for training end-to-end automatic speech recognition (E2E-ASR) systems, i.e., speech and corresponding text annotations. First, the iteratively-trained timestamp estimator (ITSE) algorithm is employed to align the speech with their corresponding annotated text symbols. Then, a speech encoder is used to convert the speech into speech embeddings. Finally, we compare the speech embeddings distances of different text symbols to obtain ATPC. Experimental results on Mandarin show that ATPC enhances E2E-ASR performance in contextual biasing and holds promise for dialects or languages lacking artificial pronunciation lexicons. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_00804 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasing Cheng, Gaofeng Lu, Haitian Yang, Chengxu Wang, Xuyang Li, Ta Yan, Yonghong Audio and Speech Processing Computation and Language Effectively distinguishing the pronunciation correlations between different written texts is a significant issue in linguistic acoustics. Traditionally, such pronunciation correlations are obtained through manually designed pronunciation lexicons. In this paper, we propose a data-driven method to automatically acquire these pronunciation correlations, called automatic text pronunciation correlation (ATPC). The supervision required for this method is consistent with the supervision needed for training end-to-end automatic speech recognition (E2E-ASR) systems, i.e., speech and corresponding text annotations. First, the iteratively-trained timestamp estimator (ITSE) algorithm is employed to align the speech with their corresponding annotated text symbols. Then, a speech encoder is used to convert the speech into speech embeddings. Finally, we compare the speech embeddings distances of different text symbols to obtain ATPC. Experimental results on Mandarin show that ATPC enhances E2E-ASR performance in contextual biasing and holds promise for dialects or languages lacking artificial pronunciation lexicons. |
| title | Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasing |
| topic | Audio and Speech Processing Computation and Language |
| url | https://arxiv.org/abs/2501.00804 |