Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.18715 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908338100371456 |
|---|---|
| author | Chen, Tuochao Wang, Qirui He, Runlin Gollakota, Shyam |
| author_facet | Chen, Tuochao Wang, Qirui He, Runlin Gollakota, Shyam |
| contents | Imagine being in a crowded space where people speak a different language and having hearables that transform the auditory space into your native language, while preserving the spatial cues for all speakers. We introduce spatial speech translation, a novel concept for hearables that translate speakers in the wearer's environment, while maintaining the direction and unique voice characteristics of each speaker in the binaural output. To achieve this, we tackle several technical challenges spanning blind source separation, localization, real-time expressive translation, and binaural rendering to preserve the speaker directions in the translated audio, while achieving real-time inference on the Apple M2 silicon. Our proof-of-concept evaluation with a prototype binaural headset shows that, unlike existing models, which fail in the presence of interference, we achieve a BLEU score of up to 22.01 when translating between languages, despite strong interference from other speakers in the environment. User studies further confirm the system's effectiveness in spatially rendering the translated speech in previously unseen real-world reverberant environments. Taking a step back, this work marks the first step towards integrating spatial perception into speech translation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18715 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spatial Speech Translation: Translating Across Space With Binaural Hearables Chen, Tuochao Wang, Qirui He, Runlin Gollakota, Shyam Computation and Language Sound Audio and Speech Processing Imagine being in a crowded space where people speak a different language and having hearables that transform the auditory space into your native language, while preserving the spatial cues for all speakers. We introduce spatial speech translation, a novel concept for hearables that translate speakers in the wearer's environment, while maintaining the direction and unique voice characteristics of each speaker in the binaural output. To achieve this, we tackle several technical challenges spanning blind source separation, localization, real-time expressive translation, and binaural rendering to preserve the speaker directions in the translated audio, while achieving real-time inference on the Apple M2 silicon. Our proof-of-concept evaluation with a prototype binaural headset shows that, unlike existing models, which fail in the presence of interference, we achieve a BLEU score of up to 22.01 when translating between languages, despite strong interference from other speakers in the environment. User studies further confirm the system's effectiveness in spatially rendering the translated speech in previously unseen real-world reverberant environments. Taking a step back, this work marks the first step towards integrating spatial perception into speech translation. |
| title | Spatial Speech Translation: Translating Across Space With Binaural Hearables |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2504.18715 |