A Study on Speech Assessment with Visual Cues
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909645999702016 |
|---|---|
| author | Ahmed, Shafique Zezario, Ryandhimas E. Saleem, Nasir Hussain, Amir Wang, Hsin-Min Tsao, Yu |
| author_facet | Ahmed, Shafique Zezario, Ryandhimas E. Saleem, Nasir Hussain, Amir Wang, Hsin-Min Tsao, Yu |
| contents | Non-intrusive assessment of speech quality and intelligibility is essential when clean reference signals are unavailable. In this work, we propose a multimodal framework that integrates audio features and visual cues to predict PESQ and STOI scores. It employs a dual-branch architecture, where spectral features are extracted using STFT, and visual embeddings are obtained via a visual encoder. These features are then fused and processed by a CNN-BLSTM with attention, followed by multi-task learning to simultaneously predict PESQ and STOI. Evaluations on the LRS3-TED dataset, augmented with noise from the DEMAND corpus, show that our model outperforms the audio-only baseline. Under seen noise conditions, it improves LCC by 9.61% (0.8397->0.9205) for PESQ and 11.47% (0.7403->0.8253) for STOI. These results highlight the effectiveness of incorporating visual cues in enhancing the accuracy of non-intrusive speech assessment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_09549 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Study on Speech Assessment with Visual Cues Ahmed, Shafique Zezario, Ryandhimas E. Saleem, Nasir Hussain, Amir Wang, Hsin-Min Tsao, Yu Audio and Speech Processing Sound Signal Processing Non-intrusive assessment of speech quality and intelligibility is essential when clean reference signals are unavailable. In this work, we propose a multimodal framework that integrates audio features and visual cues to predict PESQ and STOI scores. It employs a dual-branch architecture, where spectral features are extracted using STFT, and visual embeddings are obtained via a visual encoder. These features are then fused and processed by a CNN-BLSTM with attention, followed by multi-task learning to simultaneously predict PESQ and STOI. Evaluations on the LRS3-TED dataset, augmented with noise from the DEMAND corpus, show that our model outperforms the audio-only baseline. Under seen noise conditions, it improves LCC by 9.61% (0.8397->0.9205) for PESQ and 11.47% (0.7403->0.8253) for STOI. These results highlight the effectiveness of incorporating visual cues in enhancing the accuracy of non-intrusive speech assessment. |
| title | A Study on Speech Assessment with Visual Cues |
| topic | Audio and Speech Processing Sound Signal Processing |
| url | https://arxiv.org/abs/2506.09549 |