Adaptive Bayesian compressed sensing based on speech frame signal
- Resource Type
- Conference
- Authors
- Qian, Yongqing; Chen, Weizhen
- Source
- 2017 IEEE 9th International Conference on Communication Software and Networks (ICCSN) Communication Software and Networks (ICCSN), 2017 IEEE 9th International Conference on. :1047-1051 May, 2017
- Subject
- Communication, Networking and Broadcast Technologies
Speech
Speech processing
Compressed sensing
Discrete cosine transforms
Bayes methods
Matching pursuit algorithms
Energy measurement
Bayesian compressed sensing
energy adaption
position adaption
speech frame
- Language
- ISSN
- 2472-8489
Compressed Sensing (CS) is an emerging theory which can sample the sparse signal or compressible signal via sub-Nyquist sampling rate and reconstruct the original signal with small amount of measurements. Since speech signal is sparse in Discrete Cosine Transform (DCT) domain, a kind of adaptive Bayesian Compressed Sensing (BCS) based on speech signal is proposed in this paper. In the one hand, our proposed method exploits the difference of energy within different speech frame to allot measurements adaptively for each speech frame aim to promote the quality of recovery speech signal. In the other hand, the position information of sparse coefficient in each speech frame is also utilized by our proposed method to recover its neighboring speech frame for reducing the recovery time of speech signal. The experimental results prove that our proposed method is surely effective and practical.