Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909459010289664 |
|---|---|
| author | Hu, Jiliang Li, Zuchao Shen, Mengjia Ai, Haojun Li, Sheng Zhang, Jun |
| author_facet | Hu, Jiliang Li, Zuchao Shen, Mengjia Ai, Haojun Li, Sheng Zhang, Jun |
| contents | Spoken language understanding (SLU) is a structure prediction task in the field of speech. Recently, many works on SLU that treat it as a sequence-to-sequence task have achieved great success. However, This method is not suitable for simultaneous speech recognition and understanding. In this paper, we propose a joint speech recognition and structure learning framework (JSRSL), an end-to-end SLU model based on span, which can accurately transcribe speech and extract structured content simultaneously. We conduct experiments on name entity recognition and intent classification using the Chinese dataset AISHELL-NER and the English dataset SLURP. The results show that our proposed method not only outperforms the traditional sequence-to-sequence method in both transcription and extraction capabilities but also achieves state-of-the-art performance on the two datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07329 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding Hu, Jiliang Li, Zuchao Shen, Mengjia Ai, Haojun Li, Sheng Zhang, Jun Sound Computation and Language Audio and Speech Processing Spoken language understanding (SLU) is a structure prediction task in the field of speech. Recently, many works on SLU that treat it as a sequence-to-sequence task have achieved great success. However, This method is not suitable for simultaneous speech recognition and understanding. In this paper, we propose a joint speech recognition and structure learning framework (JSRSL), an end-to-end SLU model based on span, which can accurately transcribe speech and extract structured content simultaneously. We conduct experiments on name entity recognition and intent classification using the Chinese dataset AISHELL-NER and the English dataset SLURP. The results show that our proposed method not only outperforms the traditional sequence-to-sequence method in both transcription and extraction capabilities but also achieves state-of-the-art performance on the two datasets. |
| title | Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding |
| topic | Sound Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.07329 |