RBF models for detection of human speech in structured noise

This paper describes research to develop an efficient system that provides a binary decision as to the presence of speech in a short (one to three second) time sample of an acoustic signal. A method which is efficient and reliably detects human speech in the presence of structured noise (such as wind, music, traffic sounds, etc.) is described. There are methods which work well to detect speech in a communications environment, but previous methods can not distinguish speech from quasi-periodic signal that have a spectral power density similar to speech (such as music). Two separate feature sets are evaluated. Reliable detection is obtained down to signal to noise ratios (SNR) as low as 0 dB. The algorithm utilized is a statistical pattern classifier utilizing radial basis function (RBF) networks. Mel-cepstra and wavelet feature vectors are compared. A method of obtaining temporal feature information is described.<>