Microphone Array Signal Processing and Deep Learning for Speech Enhancement
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912185955909632 |
|---|---|
| author | Haeb-Umbach, Reinhold Nakatani, Tomohiro Delcroix, Marc Boeddeker, Christoph Ochiai, Tsubasa |
| author_facet | Haeb-Umbach, Reinhold Nakatani, Tomohiro Delcroix, Marc Boeddeker, Christoph Ochiai, Tsubasa |
| contents | Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal enhancement. However, the textbook solutions for optimal data-dependent spatial filtering rest on the knowledge of second-order statistical moments of the signals, which have traditionally been difficult to acquire. In this contribution, we compare model-based, purely data-driven, and hybrid approaches to parameter estimation and filtering, where the latter tries to combine the benefits of model-based signal processing and data-driven deep learning to overcome their individual deficiencies. We illustrate the underlying design principles with examples from noise reduction, source separation, and dereverberation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07215 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Microphone Array Signal Processing and Deep Learning for Speech Enhancement Haeb-Umbach, Reinhold Nakatani, Tomohiro Delcroix, Marc Boeddeker, Christoph Ochiai, Tsubasa Audio and Speech Processing Sound Signal Processing Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal enhancement. However, the textbook solutions for optimal data-dependent spatial filtering rest on the knowledge of second-order statistical moments of the signals, which have traditionally been difficult to acquire. In this contribution, we compare model-based, purely data-driven, and hybrid approaches to parameter estimation and filtering, where the latter tries to combine the benefits of model-based signal processing and data-driven deep learning to overcome their individual deficiencies. We illustrate the underlying design principles with examples from noise reduction, source separation, and dereverberation. |
| title | Microphone Array Signal Processing and Deep Learning for Speech Enhancement |
| topic | Audio and Speech Processing Sound Signal Processing |
| url | https://arxiv.org/abs/2501.07215 |