An improved word detection algorithm for telephone quality speech

Accurate location of the endpoints of spoken words and phrases is important for reliable and robust speech recognition. The endpoint detection problem is fairly straightforward for high‐level speech signals in low‐level stationary noise environments (e.g., signal‐to‐noise ratios greater than 30 dB). However, this problem becomes considerably more difficult when either the speech signals are too low in level (relative to the background noise), or when the background noise becomes highly nonstationary. Such conditions are often encountered in the switched telephone network when the limitation on using local dialed‐up lines are removed. In such cases the background noise is often highly variable in both level and spectral content due to transmission line distortions, transients, and tones from the line and/or from signal generators, etc. Conventional speech endpoint detectors have been shown to perform very poorly (on the order of 50% word detection) over these conditions. In this talk we present an improved...