A Study on Zero-shot Non-intrusive Speech Assessment using Large Language Models
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_ | 1866917897725542400 |
|---|---|
| author | Zezario, Ryandhimas E. Siniscalchi, Sabato M. Wang, Hsin-Min Tsao, Yu |
| author_facet | Zezario, Ryandhimas E. Siniscalchi, Sabato M. Wang, Hsin-Min Tsao, Yu |
| contents | This work investigates two strategies for zero-shot non-intrusive speech assessment leveraging large language models. First, we explore the audio analysis capabilities of GPT-4o. Second, we propose GPT-Whisper, which uses Whisper as an audio-to-text module and evaluates the naturalness of text via targeted prompt engineering. We evaluate the assessment metrics predicted by GPT-4o and GPT-Whisper, examining their correlation with human-based quality and intelligibility assessments and the character error rate (CER) of automatic speech recognition. Experimental results show that GPT-4o alone is less effective for audio analysis, while GPT-Whisper achieves higher prediction accuracy, has moderate correlation with speech quality and intelligibility, and has higher correlation with CER. Compared to SpeechLMScore and DNSMOS, GPT-Whisper excels in intelligibility metrics, but performs slightly worse than SpeechLMScore in quality estimation. Furthermore, GPT-Whisper outperforms supervised non-intrusive models MOS-SSL and MTI-Net in Spearman's rank correlation for CER of Whisper. These findings validate GPT-Whisper's potential for zero-shot speech assessment without requiring additional training data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09914 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Study on Zero-shot Non-intrusive Speech Assessment using Large Language Models Zezario, Ryandhimas E. Siniscalchi, Sabato M. Wang, Hsin-Min Tsao, Yu Audio and Speech Processing Sound This work investigates two strategies for zero-shot non-intrusive speech assessment leveraging large language models. First, we explore the audio analysis capabilities of GPT-4o. Second, we propose GPT-Whisper, which uses Whisper as an audio-to-text module and evaluates the naturalness of text via targeted prompt engineering. We evaluate the assessment metrics predicted by GPT-4o and GPT-Whisper, examining their correlation with human-based quality and intelligibility assessments and the character error rate (CER) of automatic speech recognition. Experimental results show that GPT-4o alone is less effective for audio analysis, while GPT-Whisper achieves higher prediction accuracy, has moderate correlation with speech quality and intelligibility, and has higher correlation with CER. Compared to SpeechLMScore and DNSMOS, GPT-Whisper excels in intelligibility metrics, but performs slightly worse than SpeechLMScore in quality estimation. Furthermore, GPT-Whisper outperforms supervised non-intrusive models MOS-SSL and MTI-Net in Spearman's rank correlation for CER of Whisper. These findings validate GPT-Whisper's potential for zero-shot speech assessment without requiring additional training data. |
| title | A Study on Zero-shot Non-intrusive Speech Assessment using Large Language Models |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2409.09914 |