Foreground Speech Segmentation using Zero Frequency Filtered Signal

A method for the robust segmentation of f reground speechin the presence of background degradationusing zero frequency filtered signal (ZFFS) is proposed. The speech signal from the desired speaker collected over a mobile phone is termed as foreground speechand the acoustic background picked by the same sensor that includes both speech and non-speech sources is termed asbackground degradation . The zero frequency filtering (ZFF) of speech allows only information around the zero frequency to pass through. The features from the resulting ZFFS, namely, the normalized first order autocorrelation coefficient and the strength of excitation of ZFFS are observed to be different for foreground speech and background degradation. A method for foreground speech segmentation is developed using these two features. The evaluation using utterances containing isolated words of foreground speech and background degradation collected in a real environment shows a robust foreground speech segmentation.