Automatic speaker age and gender recognition using acoustic and prosodic level information fusion

The paper presents a novel automatic speaker age and gender identification approach which combines seven different methods t both acoustic and prosodic levels to improve the baseline performance. The three baseline subsystems are (1) Gaussian mixture odel (GMM) based on mel-frequency cepstral coefficient (MFCC) features, (2) Support vector machine (SVM) based on GMM ean supervectors and (3) SVM based on 450-dimensional utterance level features including acoustic, prosodic and voice quality nformation. In addition, we propose four subsystems: (1) SVM based on UBM weight posterior probability supervectors using the hattacharyya probability product kernel, (2) Sparse representation based on UBM weight posterior probability supervectors, (3) VM based on GMM maximum likelihood linear regression (MLLR) matrix supervectors and (4) SVM based on the polynomial xpansion coefficients of the syllable level prosodic feature contours in voiced speech segments. Contours of pitch, time domain nergy, frequency domain harmonic structure energy and formant for each syllable (segmented using energy information in the voiced peech segment) are considered for analysis in subsystem (4). The proposed four subsystems have been demonstrated to be effective nd able to achieve competitive results in classifying different age and gender groups. To further improve the overall classification erformance, weighted summation based fusion of these seven subsystems at the score level is demonstrated. Experiment results re reported on the development and test set of the 2010 Interspeech Paralinguistic Challenge aGender database. Compared to the VM baseline system (3), which is the baseline system suggested by the challenge committee, the proposed fusion system achieves .6% absolute improvement in unweighted accuracy for the age task and 4.2% for the gender task on the development set. On the nal test set, we obtain 3.1% and 3.8% absolute improvement, respectively. 2012 Elsevier Ltd. All rights reserved.