Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.21004 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915650010611712 |
|---|---|
| author | He, Lixing Guo, Yunqi Yan, Zhenyu Xing, Guoliang |
| author_facet | He, Lixing Guo, Yunqi Yan, Zhenyu Xing, Guoliang |
| contents | In crowded places such as conferences, background noise, overlapping voices, and lively interactions make it difficult to have clear conversations. This situation often worsens the phenomenon known as "cocktail party deafness." We present ClearSphere, the collaborative system that enhances speech at the conversation level with multi-earphones. Real-time conversation enhancement requires a holistic modeling of all the members in the conversation, and an effective way to extract the speech from the mixture. ClearSphere bridges the acoustic sensor system and state-of-the-art deep learning for target speech extraction by making two key contributions: 1) a conversation-driven network protocol, and 2) a robust target conversation extraction model. Our networking protocol enables mobile, infrastructure-free coordination among earphone devices. Our conversation extraction model can leverage the relay audio in a bandwidth-efficient way. ClearSphere is evaluated in both real-world experiments and simulations. Results show that our conversation network obtains more than 90\% accuracy in group formation, improves the speech quality by up to 8.8 dB over state-of-the-art baselines, and demonstrates real-time performance on a mobile device. In a user study with 20 participants, ClearSphere has a much higher score than baseline with good usability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21004 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoHear: Conversation Enhancement via Multi-Earphone Collaboration He, Lixing Guo, Yunqi Yan, Zhenyu Xing, Guoliang Sound In crowded places such as conferences, background noise, overlapping voices, and lively interactions make it difficult to have clear conversations. This situation often worsens the phenomenon known as "cocktail party deafness." We present ClearSphere, the collaborative system that enhances speech at the conversation level with multi-earphones. Real-time conversation enhancement requires a holistic modeling of all the members in the conversation, and an effective way to extract the speech from the mixture. ClearSphere bridges the acoustic sensor system and state-of-the-art deep learning for target speech extraction by making two key contributions: 1) a conversation-driven network protocol, and 2) a robust target conversation extraction model. Our networking protocol enables mobile, infrastructure-free coordination among earphone devices. Our conversation extraction model can leverage the relay audio in a bandwidth-efficient way. ClearSphere is evaluated in both real-world experiments and simulations. Results show that our conversation network obtains more than 90\% accuracy in group formation, improves the speech quality by up to 8.8 dB over state-of-the-art baselines, and demonstrates real-time performance on a mobile device. In a user study with 20 participants, ClearSphere has a much higher score than baseline with good usability. |
| title | CoHear: Conversation Enhancement via Multi-Earphone Collaboration |
| topic | Sound |
| url | https://arxiv.org/abs/2505.21004 |