Speaker identification from shouted speech: Analysis and compensation

Text-independent speaker identification is studied using neutral and shouted speech in Finnish to analyze the effect of vocal mode mismatch between training and test utterances. Standard mel-frequency cepstral coefficient (MFCC) features with Gaussian mixture model (GMM) recognizer are used for speaker identification. The results indicate that speaker identification accuracy reduces from perfect (100 %) to 8.71 % under vocal mode mismatch. Because of this dramatic degradation in recognition accuracy, we propose to use a joint density GMM mapping technique for compensating the MFCC features. This mapping is trained on a disjoint emotional speech corpus to create a completely speaker- and speech mode independent emotion-neutralizing mapping. As a result of the compensation, the 8.71 % identification accuracy increases to 32.00 % without degrading the non-mismatched train-test conditions much.

[1]  John H. L. Hansen,et al.  Analysis and classification of speech mode: whispered through shouted , 2007, INTERSPEECH.

[2]  Moncef Gabbouj,et al.  On the impact of alignment on voice conversion performance , 2008, INTERSPEECH.

[3]  Andreas Stolcke,et al.  The SRI NIST 2010 speaker recognition evaluation system , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  J Elliott.  Comparing the Acoustic Properties of Normal and Shouted Speech: A Study in Forensic Phonetics , 2000 .

[5]  Roland Auckenthaler,et al.  Score Normalization for Text-Independent Speaker Verification Systems , 2000, Digit. Signal Process..

[6]  Sridha Sridharan,et al.  Feature warping for robust speaker verification , 2001, Odyssey.

[7]  Ismail Shahin.  Employing Second-Order Circular Suprasegmental Hidden Markov Models to Enhance Speaker Identification Performance in Shouted Talking Environments , 2010, EURASIP J. Audio Speech Music. Process..

[8]  Yannis Stylianou,et al.  Voice Transformation: A survey , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  Douglas A. Reynolds,et al.  Robust text-independent speaker identification using Gaussian mixture speaker models , 1995, IEEE Trans. Speech Audio Process..

[10]  Alvin F. Martin,et al.  Report on Performance Results in the NIST 2010 Speaker Recognition Evaluation , 2011, INTERSPEECH.

[11]  Astrid Paeschke,et al.  A database of German emotional speech , 2005, INTERSPEECH.

[12]  Paavo Alku,et al.  Shout detection in noise , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  Patrick Kenny,et al.  Joint Factor Analysis of Speaker and Session Variability: Theory and Algorithms , 2006 .

[14]  Hideki Kawahara,et al.  Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds , 1999, Speech Commun..

[15]  Takanobu Nishiura,et al.  Acoustic-Based Security System: Towards Robust Understanding of Emergency Shout , 2009, 2009 Fifth International Conference on Information Assurance and Security.

[16]  Eric Moulines,et al.  Continuous probabilistic transform for voice conversion , 1998, IEEE Trans. Speech Audio Process..

[17]  Alexander Kain,et al.  Spectral voice conversion for text-to-speech synthesis , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).