BLIND SPEECH SEPARATION USING FRACTIONAL ORDER MOMENTS

A new contrast function based on low fractional moments is proposed for blind source separation (BSS) of speech signals. Its study is motivated by a need to perform blind speech separation over short data frames. The new contrast function is more numerically stable; its estimates over short frames have better statistical properties than higher order measures such as kurtosis. The proposed contrast function is enabled by the Laplacian distribution of speech signals. Its theoretical and statistical properties are derived and tested using pseudo-random data as well as speech. Its performance is compared to that of kurtosis and show to consistently outperform the normalized kurtosis over a wide range of frame lengths chosen between 5 and 500 ms.