Noise reduction optimization of sound sensor based on a Conditional Generation Adversarial Network
Paper i proceeding, 2021

To address the problems in the traditional speech signal noise elimination methods, such as the residual noise, poor real-time performance and narrow applications a new method is proposed to eliminate network voice noise based on deep learning of conditional generation adversarial network. In terms of the perceptual evaluation of speech quality (PESQ) and shorttime objective intelligibility measure (STOI) functions used as the loss function in the neural network, which were used as the loss function in the neural network, the flexibility of the whole network was optimized, and the training process of the model simplified. The experimental results indicate that, under the noisy environment, especially in a restaurant, the proposed noise reduction scheme improves the STOI score by 26.23% and PESQ score by 17.18%, respectively, compared with the traditional Wiener noise reduction algorithm. Therefore, the sound sensor's noise reduction scheme through our approach has achieved a remarkable noise reduction effect, more useful information transmission, and stronger practicability.

Författare

Xiongwei Lin

Guangdong University of Technology

Dongru Yang

Guangdong University of Technology

Yadong Mao

Student vid Chalmers

Lei Zhou

Guangdong University of Technology

Xiaobo Zhao

Guangdong University of Technology

Shengguo Lu

Guangdong University of Technology

Journal of Physics: Conference Series

17426588 (ISSN) 17426596 (eISSN)

Vol. 1873 1 012034

2021 2nd International Workshop on Electronic communication and Artificial Intelligence, IWECAI 2021
Nanjing, China,

Ämneskategorier

Telekommunikation

Kommunikationssystem

Signalbehandling

DOI

10.1088/1742-6596/1873/1/012034

Mer information

Senast uppdaterat

2021-05-12