Single-channel speaker-dependent speech enhancement exploiting generic noise model learned by non-negative matrix factorization
- Resource Type
- Conference
- Authors
- Duong, Hien-Thanh T.; Nguyen, Quoc-Cuong; Nguyen, Cong-Phuong; Duong, Ngoc Q. K.
- Source
- 2016 International Conference on Electronics, Information, and Communications (ICEIC) Electronics, Information, and Communications (ICEIC), 2016 International Conference on. :1-4 Jan, 2016
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Fields, Waves and Electromagnetics
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Speech
Speech enhancement
Training
Spectrogram
Parameter estimation
Source separation
Speaker-dependent speech enhancement
non-negative matrix factorization
group sparsity
generic spectral model
- Language
This paper considers the single-channel speech separation problem given a noisy observation recorded by a microphone. More precisely, we focus on the speaker-dependent approach where spectral characteristic of target speech is learned in advance from a clean example. In training process, we propose to learn a generic spectral model for noise source by collecting various types of environmental noise via the established non-negative matrix factorization framework. In speech enhancement process, we propose to combine two existing group sparsity-inducing penalties in the optimization function and derive the corresponding algorithm for parameter estimation based on multiplicative update (MU) rule. Experiment result over mixtures containing different real-world noises confirms the effectiveness of our approach.