A system is proposed for the automatic detection of high vocal effort in speech. The system is evaluated using both PCM-coded speech and AMRcoded telephone speech. In addition, the effect of far-end noise in the telephone conditions is studied using both matched-condition training and cases with additive noise mismatch. The proposed system is based on Bayesian classification of mel-frequency cepstral feature vectors. Concerning the MFCC feature extraction process, the substitution of a spectrum analysis method emphasizing the fine structure improves the results in the noisy cases.
Index Terms: vocal effort detection, speech analysis
Bibliographic reference. Pohjalainen, Jouni / Raitio, Tuomo / Pulakka, Hannu / Alku, Paavo (2012): "Automatic detection of high vocal effort in telephone speech", In INTERSPEECH-2012, 691-694.