Frontend Token Enhancement for Token-Based Speech Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912875260411904 |
|---|---|
| author | Ashihara, Takanori Horiguchi, Shota Matsuura, Kohei Ochiai, Tsubasa Delcroix, Marc |
| author_facet | Ashihara, Takanori Horiguchi, Shota Matsuura, Kohei Ochiai, Tsubasa Delcroix, Marc |
| contents | Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such as semantic or phonetic tokens derived from clustering outputs of self-supervised learning (SSL) speech models, are susceptible to environmental noise, which can degrade backend task performance. In this work, we introduce a frontend system that estimates clean speech tokens from noisy speech and evaluate it on an ASR backend using semantic tokens. We consider four types of enhancement models based on their input/output domains: wave-to-wave, token-to-token, continuous SSL features-to-token, and wave-to-token. These models are trained independently of ASR backends. Experiments on the CHiME-4 dataset demonstrate that wave-to-token enhancement achieves the best performance among the frontends. Moreover, it mostly outperforms the ASR system based on continuous SSL features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04217 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Frontend Token Enhancement for Token-Based Speech Recognition Ashihara, Takanori Horiguchi, Shota Matsuura, Kohei Ochiai, Tsubasa Delcroix, Marc Sound Computation and Language Audio and Speech Processing Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such as semantic or phonetic tokens derived from clustering outputs of self-supervised learning (SSL) speech models, are susceptible to environmental noise, which can degrade backend task performance. In this work, we introduce a frontend system that estimates clean speech tokens from noisy speech and evaluate it on an ASR backend using semantic tokens. We consider four types of enhancement models based on their input/output domains: wave-to-wave, token-to-token, continuous SSL features-to-token, and wave-to-token. These models are trained independently of ASR backends. Experiments on the CHiME-4 dataset demonstrate that wave-to-token enhancement achieves the best performance among the frontends. Moreover, it mostly outperforms the ASR system based on continuous SSL features. |
| title | Frontend Token Enhancement for Token-Based Speech Recognition |
| topic | Sound Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2602.04217 |