Spectral and textural feature-based system for automatic detection of fricatives and affricates

Phoneme spotting in continuous speech has various applications - in speech recognition, smart audio filtering, multimedia synchronization and other fields. Many studies on phoneme spotting have been conducted, using different approaches. We present two algorithms for spotting fricatives (such as /s/, /sh/, /f/) and affricates (/ts/, /ch/) - one based on a cepstrogram-matching approach, and the other on an LDA classifier with a feature vector constructed from temporal, spectral and textural features of the audio signal. Tested on a selection of speech and song recordings, the algorithms demonstrate correct identification rate of over 90% and specificity of over 85%.