Automatic discrimination between laughter and speech

• Published in: Speech communication Vol. 49; no. 2; pp. 144 - 158
• Main Authors: Truong, Khiet P., van Leeuwen, David A.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.02.2007; Elsevier; Elsevier : North-Holland
• Subjects: Applied sciences; Artificial intelligence; Automatic detection emotion; Automatic detection laughter; Computer science; control theory; systems; Connectionism. Neural networks; Exact sciences and technology; Information, signal and communications theory; Signal and communications theory; Signal processing; Signal representation. Spectral analysis; Signal, noise; Speech processing; Telecommunications and information theory; Automatic detection emotion; Automatic detection laughter; Performance evaluation; Emotion recognition; Discriminant analysis; Automatic classification; Acoustic measurement; Acoustic signal; Sex; Error rate; Mixture theory; Support vector machine; Speaker recognition; Signal classification; Intonation; Discrimination; Gaussian process; Prosody; Automatic measurement; Multilayer perceptrons; Automatic recognition; Pitch(acoustics); Speech processing; Language recognition; Physical Sciences
• ISSN: 0167-6393; 1872-7182
• DOI: 10.1016/j.specom.2007.01.001

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.