Robust Speech Recognition with Schrödinger Bridge-Based Speech Enhancement
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908354407825408 |
|---|---|
| author | Nasretdinov, Rauf Korostik, Roman Jukić, Ante |
| author_facet | Nasretdinov, Rauf Korostik, Roman Jukić, Ante |
| contents | In this work, we investigate application of generative speech enhancement to improve the robustness of ASR models in noisy and reverberant conditions. We employ a recently-proposed speech enhancement model based on Schrödinger bridge, which has been shown to perform well compared to diffusion-based approaches. We analyze the impact of model scaling and different sampling methods on the ASR performance. Furthermore, we compare the considered model with predictive and diffusion-based baselines and analyze the speech recognition performance when using different pre-trained ASR models. The proposed approach significantly reduces the word error rate, reducing it by approximately 40% relative to the unprocessed speech signals and by approximately 8% relative to a similarly sized predictive approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04237 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Speech Recognition with Schrödinger Bridge-Based Speech Enhancement Nasretdinov, Rauf Korostik, Roman Jukić, Ante Audio and Speech Processing Sound In this work, we investigate application of generative speech enhancement to improve the robustness of ASR models in noisy and reverberant conditions. We employ a recently-proposed speech enhancement model based on Schrödinger bridge, which has been shown to perform well compared to diffusion-based approaches. We analyze the impact of model scaling and different sampling methods on the ASR performance. Furthermore, we compare the considered model with predictive and diffusion-based baselines and analyze the speech recognition performance when using different pre-trained ASR models. The proposed approach significantly reduces the word error rate, reducing it by approximately 40% relative to the unprocessed speech signals and by approximately 8% relative to a similarly sized predictive approach. |
| title | Robust Speech Recognition with Schrödinger Bridge-Based Speech Enhancement |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2505.04237 |