Transformer-based Model for ASR N-Best Rescoring and Rewriting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917691675115520 |
|---|---|
| author | Kang, Iwen E. Van Gysel, Christophe Siu, Man-Hung |
| author_facet | Kang, Iwen E. Van Gysel, Christophe Siu, Man-Hung |
| contents | Voice assistants increasingly use on-device Automatic Speech Recognition (ASR) to ensure speed and privacy. However, due to resource constraints on the device, queries pertaining to complex information domains often require further processing by a search engine. For such applications, we propose a novel Transformer based model capable of rescoring and rewriting, by exploring full context of the N-best hypotheses in parallel. We also propose a new discriminative sequence training objective that can work well for both rescore and rewrite tasks. We show that our Rescore+Rewrite model outperforms the Rescore-only baseline, and achieves up to an average 8.6% relative Word Error Rate (WER) reduction over the ASR system by itself. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08207 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transformer-based Model for ASR N-Best Rescoring and Rewriting Kang, Iwen E. Van Gysel, Christophe Siu, Man-Hung Audio and Speech Processing Computation and Language Machine Learning Sound Voice assistants increasingly use on-device Automatic Speech Recognition (ASR) to ensure speed and privacy. However, due to resource constraints on the device, queries pertaining to complex information domains often require further processing by a search engine. For such applications, we propose a novel Transformer based model capable of rescoring and rewriting, by exploring full context of the N-best hypotheses in parallel. We also propose a new discriminative sequence training objective that can work well for both rescore and rewrite tasks. We show that our Rescore+Rewrite model outperforms the Rescore-only baseline, and achieves up to an average 8.6% relative Word Error Rate (WER) reduction over the ASR system by itself. |
| title | Transformer-based Model for ASR N-Best Rescoring and Rewriting |
| topic | Audio and Speech Processing Computation and Language Machine Learning Sound |
| url | https://arxiv.org/abs/2406.08207 |