Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916412709142528 |
|---|---|
| author | Bae, Hanbin Andreev, Pavel Saginbaev, Azat Babaev, Nicholas Lee, Won-Jun Sung, Hosang Cho, Hoon-Young |
| author_facet | Bae, Hanbin Andreev, Pavel Saginbaev, Azat Babaev, Nicholas Lee, Won-Jun Sung, Hosang Cho, Hoon-Young |
| contents | This paper introduces a speech enhancement solution tailored for true wireless stereo (TWS) earbuds on-device usage. The solution was specifically designed to support conversations in noisy environments, with active noise cancellation (ANC) activated. The primary challenges for speech enhancement models in this context arise from computational complexity that limits on-device usage and latency that must be less than 3 ms to preserve a live conversation. To address these issues, we evaluated several crucial design elements, including the network architecture and domain, design of loss functions, pruning method, and hardware-specific optimization. Consequently, we demonstrated substantial improvements in speech enhancement quality compared with that in baseline models, while simultaneously reducing the computational complexity and algorithmic latency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18705 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds Bae, Hanbin Andreev, Pavel Saginbaev, Azat Babaev, Nicholas Lee, Won-Jun Sung, Hosang Cho, Hoon-Young Audio and Speech Processing Artificial Intelligence Sound Signal Processing This paper introduces a speech enhancement solution tailored for true wireless stereo (TWS) earbuds on-device usage. The solution was specifically designed to support conversations in noisy environments, with active noise cancellation (ANC) activated. The primary challenges for speech enhancement models in this context arise from computational complexity that limits on-device usage and latency that must be less than 3 ms to preserve a live conversation. To address these issues, we evaluated several crucial design elements, including the network architecture and domain, design of loss functions, pruning method, and hardware-specific optimization. Consequently, we demonstrated substantial improvements in speech enhancement quality compared with that in baseline models, while simultaneously reducing the computational complexity and algorithmic latency. |
| title | Speech Boosting: Low-Latency Live Speech Enhancement for TWS Earbuds |
| topic | Audio and Speech Processing Artificial Intelligence Sound Signal Processing |
| url | https://arxiv.org/abs/2409.18705 |