Automatic discrimination between laughter and speech

DMCA

Automatic discrimination between laughter and speech

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Khiet P. Truong , David A. Van Leeuwen

Venue:	Speech Communication
Citations:	55 - 2 self

BibTeX

@ARTICLE{Truong_automaticdiscrimination,
    author = {Khiet P. Truong and David A. Van Leeuwen},
    title = {Automatic discrimination between laughter and speech},
    journal = {Speech Communication},
    year = {},
    volume = {49},
    pages = {144--158}
}

OpenURL

Abstract

Emotions can be recognized by audible paralinguistic cues in speech. By detecting these paralinguistic cues that can consist of laughter, a trembling voice, coughs, changes in the intonation contour etc., information about the speaker’s state and emotion can be revealed. This paper describes the development of a gender-independent laugh detector with the aim to enable automatic emotion recognition. Different types of features (spectral, prosodic) for laughter detection were investigated using different classification techniques (Gaussian Mixture Models, Support Vector Machines, Multi Layer Perceptron) often used in language and speaker recognition. Classification experiments were carried out with short pre-segmented speech and laughter segments extracted from the ICSI Meeting Recorder Corpus (with a mean duration of approximately 2 s). Equal error rates of around 3 % were obtained when tested on speaker-independent speech data. We found that a fusion between classifiers based on Gaussian Mixture Models and classifiers based on Support Vector Machines increases discriminative power. We also found that a fusion between classifiers that use spectral features and classifiers that use prosodic information usually increases the performance for discrimination between laughter and speech. Our acoustic measurements showed differences between laughter and speech in mean pitch and in the ratio of the durations of unvoiced to voiced portions, which indicate that these prosodic features are indeed useful for discrimination between laughter and speech.

Keyphrases

automatic discrimination support vector machine gaussian mixture model gender-independent laugh detector trembling voice speaker state short pre-segmented speech acoustic measurement automatic emotion recognition paralinguistic cue intonation contour etc laughter detection audible paralinguistic cue mean duration prosodic information mean pitch discriminative power speaker recognition spectral feature icsi meeting recorder corpus multi layer perceptron prosodic feature voiced portion different type equal error rate laughter segment classification experiment speaker-independent speech data different classification technique

DMCA