Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners
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_ | 1866918086280478720 |
|---|---|
| author | Yamamoto, Katsuhiko Miyazaki, Koichi |
| author_facet | Yamamoto, Katsuhiko Miyazaki, Koichi |
| contents | Speech intelligibility prediction (SIP) models have been used as objective metrics to assess intelligibility for hearing-impaired (HI) listeners. In the Clarity Prediction Challenge 2 (CPC2), non-intrusive binaural SIP models based on transformers showed high prediction accuracy. However, the self-attention mechanism theoretically incurs high computational and memory costs, making it a bottleneck for low-latency, power-efficient devices. This may also degrade the temporal processing of binaural SIPs. Therefore, we propose Mamba-based SIP models instead of transformers for the temporal processing blocks. Experimental results show that our proposed SIP model achieves competitive performance compared to the baseline while maintaining a relatively small number of parameters. Our analysis suggests that the SIP model based on bidirectional Mamba effectively captures contextual and spatial speech information from binaural signals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05729 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners Yamamoto, Katsuhiko Miyazaki, Koichi Sound Audio and Speech Processing Speech intelligibility prediction (SIP) models have been used as objective metrics to assess intelligibility for hearing-impaired (HI) listeners. In the Clarity Prediction Challenge 2 (CPC2), non-intrusive binaural SIP models based on transformers showed high prediction accuracy. However, the self-attention mechanism theoretically incurs high computational and memory costs, making it a bottleneck for low-latency, power-efficient devices. This may also degrade the temporal processing of binaural SIPs. Therefore, we propose Mamba-based SIP models instead of transformers for the temporal processing blocks. Experimental results show that our proposed SIP model achieves competitive performance compared to the baseline while maintaining a relatively small number of parameters. Our analysis suggests that the SIP model based on bidirectional Mamba effectively captures contextual and spatial speech information from binaural signals. |
| title | Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.05729 |