Musical-noise-free blind speech extraction integrating microphone array and iterative spectral subtraction
| Autor: | Ryoichi Miyazaki, Kazunobu Kondo, Jonathan Blanchette, Kiyohiro Shikano, Satoshi Nakamura, Martin Bouchard, Hiroshi Saruwatari |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Microphone array
Channel (digital image) Computer science Blind speech extraction Speech recognition Wiener filter Estimator Higher-order statistics Independent component analysis Speech enhancement Noise symbols.namesake Computer Science::Sound Control and Systems Engineering Signal Processing symbols Iterative spectral subtraction Computer Vision and Pattern Recognition Electrical and Electronic Engineering Software |
| Zdroj: | Signal Processing. 102:226-239 |
| ISSN: | 0165-1684 |
| DOI: | 10.1016/j.sigpro.2014.03.010 |
| Popis: | In this paper, we propose a musical-noise-free blind speech extraction method using a microphone array for application to nonstationary noise. In our previous study, it was found that optimized iterative spectral subtraction (SS) results in speech enhancement with almost no musical noise generation, but this method is valid only for stationary noise. The proposed method consists of iterative blind dynamic noise estimation by, e.g., independent component analysis (ICA) or multichannel Wiener filtering, and musical-noise-free speech extraction by modified iterative SS, where multiple iterative SS is applied to each channel while maintaining the multichannel property reused for the dynamic noise estimators. Also, in relation to the proposed method, we discuss the justification of applying ICA to signals nonlinearly distorted by SS. From objective and subjective evaluations simulating a real-world hands-free speech communication system, we reveal that the proposed method outperforms the conventional methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect