A simple and efficient algorithm is presented to separate concurrent speeches. The parameters of mixed speeches are estimated by searching in the neighbor area of given pitches to minimize the error between the origin...A simple and efficient algorithm is presented to separate concurrent speeches. The parameters of mixed speeches are estimated by searching in the neighbor area of given pitches to minimize the error between the original and the synthetic spectrums. The effectiveness of the proposed algorithm to separate close frequencies is demonstrated.展开更多
基金Supported by the National Natural Science Foundation of China(No.60172048)
文摘A simple and efficient algorithm is presented to separate concurrent speeches. The parameters of mixed speeches are estimated by searching in the neighbor area of given pitches to minimize the error between the original and the synthetic spectrums. The effectiveness of the proposed algorithm to separate close frequencies is demonstrated.