Creaky voice is used by speakers for a variety of interactive, expressive and stylistic reasons. As a result the accurate detection of creaky regions in speech can yield important information not captured within the propositional content of spoken utterances. We, hence, describe a new method for automatically detecting creaky regions following the observation that secondary peaks occur in the LP-residual signal. The proposed approach is shown through an objective evaluation on a range of speech databases to significantly outperform the state-of-the-art.

Index Terms: Voice quality, glottal source, creak, vocal fry