TokenSE: a Mamba-based discrete token speech enhancement framework for cochlear implants
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910127844491264 |
|---|---|
| author | Chiang, Hsin-Tien Hansen, John H. L. |
| author_facet | Chiang, Hsin-Tien Hansen, John H. L. |
| contents | Speech enhancement (SE) is critical for improving speech intelligibility and quality in real-world environments, particularly for cochlear implant (CI) users who experience severe degradations in speech understanding under noisy and reverberant conditions. In this study, we propose TokenSE, a discrete token-based SE framework operating in the neural audio codec space, which predicts clean codec token indices from degraded speech using a Mamba-based model. Unlike the earlier Transformer architecture, whose self-attention mechanism has a computational complexity that grows quadratically with sequence length, the input-dependent selection mechanism of Mamba achieves linear complexity, making it a compelling alternative to Transformers, especially for CI and hearing-aid (HA) applications. Objective evaluations show that TokenSE consistently outperforms baseline methods on both in-domain and out-of-domain datasets. Moreover, subjective listening experiments with CI users indicate clear benefit in speech intelligibility under adverse noisy and reverberant environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12246 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TokenSE: a Mamba-based discrete token speech enhancement framework for cochlear implants Chiang, Hsin-Tien Hansen, John H. L. Audio and Speech Processing Speech enhancement (SE) is critical for improving speech intelligibility and quality in real-world environments, particularly for cochlear implant (CI) users who experience severe degradations in speech understanding under noisy and reverberant conditions. In this study, we propose TokenSE, a discrete token-based SE framework operating in the neural audio codec space, which predicts clean codec token indices from degraded speech using a Mamba-based model. Unlike the earlier Transformer architecture, whose self-attention mechanism has a computational complexity that grows quadratically with sequence length, the input-dependent selection mechanism of Mamba achieves linear complexity, making it a compelling alternative to Transformers, especially for CI and hearing-aid (HA) applications. Objective evaluations show that TokenSE consistently outperforms baseline methods on both in-domain and out-of-domain datasets. Moreover, subjective listening experiments with CI users indicate clear benefit in speech intelligibility under adverse noisy and reverberant environments. |
| title | TokenSE: a Mamba-based discrete token speech enhancement framework for cochlear implants |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2604.12246 |