Exploring Efficient Directional and Distance Cues for Regional Speech Separation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912532304756736 |
|---|---|
| author | Jiang, Yiheng Wang, Haoxu Chen, Yafeng Qiao, Gang Tian, Biao |
| author_facet | Jiang, Yiheng Wang, Haoxu Chen, Yafeng Qiao, Gang Tian, Biao |
| contents | In this paper, we introduce a neural network-based method for regional speech separation using a microphone array. This approach leverages novel spatial cues to extract the sound source not only from specified direction but also within defined distance. Specifically, our method employs an improved delay-and-sum technique to obtain directional cues, substantially enhancing the signal from the target direction. We further enhance separation by incorporating the direct-to-reverberant ratio into the input features, enabling the model to better discriminate sources within and beyond a specified distance. Experimental results demonstrate that our proposed method leads to substantial gains across multiple objective metrics. Furthermore, our method achieves state-of-the-art performance on the CHiME-8 MMCSG dataset, which was recorded in real-world conversational scenarios, underscoring its effectiveness for speech separation in practical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07563 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Efficient Directional and Distance Cues for Regional Speech Separation Jiang, Yiheng Wang, Haoxu Chen, Yafeng Qiao, Gang Tian, Biao Sound Audio and Speech Processing In this paper, we introduce a neural network-based method for regional speech separation using a microphone array. This approach leverages novel spatial cues to extract the sound source not only from specified direction but also within defined distance. Specifically, our method employs an improved delay-and-sum technique to obtain directional cues, substantially enhancing the signal from the target direction. We further enhance separation by incorporating the direct-to-reverberant ratio into the input features, enabling the model to better discriminate sources within and beyond a specified distance. Experimental results demonstrate that our proposed method leads to substantial gains across multiple objective metrics. Furthermore, our method achieves state-of-the-art performance on the CHiME-8 MMCSG dataset, which was recorded in real-world conversational scenarios, underscoring its effectiveness for speech separation in practical applications. |
| title | Exploring Efficient Directional and Distance Cues for Regional Speech Separation |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2508.07563 |