Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction
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_ | 1866910645145829376 |
|---|---|
| author | Ko, Yuka Li, Sheng Yang, Chao-Han Huck Kawahara, Tatsuya |
| author_facet | Ko, Yuka Li, Sheng Yang, Chao-Han Huck Kawahara, Tatsuya |
| contents | With the strong representational power of large language models (LLMs), generative error correction (GER) for automatic speech recognition (ASR) aims to provide semantic and phonetic refinements to address ASR errors. This work explores how LLM-based GER can enhance and expand the capabilities of Japanese language processing, presenting the first GER benchmark for Japanese ASR with 0.9-2.6k text utterances. We also introduce a new multi-pass augmented generative error correction (MPA GER) by integrating multiple system hypotheses on the input side with corrections from multiple LLMs on the output side and then merging them. To the best of our knowledge, this is the first investigation of the use of LLMs for Japanese GER, which involves second-pass language modeling on the output transcriptions generated by the ASR system (e.g., N-best hypotheses). Our experiments demonstrated performance improvement in the proposed methods of ASR quality and generalization both in SPREDS-U1-ja and CSJ data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_16180 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction Ko, Yuka Li, Sheng Yang, Chao-Han Huck Kawahara, Tatsuya Audio and Speech Processing Computation and Language Sound With the strong representational power of large language models (LLMs), generative error correction (GER) for automatic speech recognition (ASR) aims to provide semantic and phonetic refinements to address ASR errors. This work explores how LLM-based GER can enhance and expand the capabilities of Japanese language processing, presenting the first GER benchmark for Japanese ASR with 0.9-2.6k text utterances. We also introduce a new multi-pass augmented generative error correction (MPA GER) by integrating multiple system hypotheses on the input side with corrections from multiple LLMs on the output side and then merging them. To the best of our knowledge, this is the first investigation of the use of LLMs for Japanese GER, which involves second-pass language modeling on the output transcriptions generated by the ASR system (e.g., N-best hypotheses). Our experiments demonstrated performance improvement in the proposed methods of ASR quality and generalization both in SPREDS-U1-ja and CSJ data. |
| title | Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction |
| topic | Audio and Speech Processing Computation and Language Sound |
| url | https://arxiv.org/abs/2408.16180 |