11th EAI International Conference on Mobile Multimedia Communications

Research Article

Single Channel Speech Enhancement Using Complex Kalman Filter in Noisy Reverberant Environments

Download92 downloads
  • @INPROCEEDINGS{10.4108/eai.21-6-2018.2276600,
        author={Yang Liu and Yanmin Shi and Xinglu Ma},
        title={Single Channel Speech Enhancement Using Complex Kalman Filter in Noisy Reverberant Environments},
        proceedings={11th EAI International Conference on Mobile Multimedia Communications},
        publisher={EAI},
        proceedings_a={MOBIMEDIA},
        year={2018},
        month={9},
        keywords={speech enhancement complex kalman filter gammatone filterbank},
        doi={10.4108/eai.21-6-2018.2276600}
    }
    
  • Yang Liu
    Yanmin Shi
    Xinglu Ma
    Year: 2018
    Single Channel Speech Enhancement Using Complex Kalman Filter in Noisy Reverberant Environments
    MOBIMEDIA
    EAI
    DOI: 10.4108/eai.21-6-2018.2276600
Yang Liu1,*, Yanmin Shi1, Xinglu Ma1
  • 1: Qingdao University of Science and Technology
*Contact email: 619543973@qq.com

Abstract

The previous research has proved that restoring the instantaneous amplitude and phase individually by linear prediction with Kalman filter on Gammatone filterbank could improve quality and intelligibility of noisy reverberant speech significantly. However, this method still suffers from the double prediction errors caused by the separated estimation for instantaneous amplitude and phase. This paper aims to study feasibility for restoring both instantaneous amplitude and phase simultaneously by complex Kalman filter to improve previous method. The signal to error ratio (SER), perceptual evaluation of speech quality (PESQ) and SNR loss were used as objective evaluation metrics. Results showed that the proposed method could effectively improve these objective metrics more than the previous method.