Speaker identification in shouted talking environments based on novel Third-Order Hidden Markov Models

In this work we propose, implement, and evaluate novel models called Third-Order Hidden Markov Models (HMM3s) to enhance low performance of text-independent speaker identification in shouted talking environments. The proposed models have been tested on our collected speech database using Mel-Frequency Cepstral Coefficients (MFCCs). Our results demonstrate that HMM3s significantly improve speaker identification performance in such talking environments by 11.3% and 166.7% compared to second-order hidden Markov models (HMM2s) and first-order hidden Markov models (HMM1s), respectively. The achieved results based on the proposed models are close to those obtained in subjective assessment by human listeners.

[1]  Sadaoki Furui.  Speaker-dependent-feature extraction, recognition and processing techniques , 1991, Speech Commun..

[2]  Jean-François Mari,et al.  A second-order HMM for high performance word and phoneme-based continuous speech recognition , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[3]  Ismail Shahin,et al.  Enhancing speaker identification performance under the shouted talking condition using second-order circular hidden Markov models , 2006, Speech Commun..

[4]  Ismail Shahin,et al.  Speaker identification in the shouted environment using Suprasegmental Hidden Markov Models , 2008, Signal Process..

[5]  Yeunung Chen,et al.  Cepstral domain talker stress compensation for robust speech recognition , 1988, IEEE Trans. Acoust. Speech Signal Process..

[6]  John H. L. Hansen,et al.  A comparative study of traditional and newly proposed features for recognition of speech under stress , 2000, IEEE Trans. Speech Audio Process..

[7]  John H. L. Hansen,et al.  The Impact of Speech Under `Stress''on Military Speech Technology , 2000 .

[8]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[9]  Abdelaziz Kriouile,et al.  Automatic word recognition based on second-order hidden Markov models , 1994, IEEE Trans. Speech Audio Process..

[10]  K E Cummings,et al.  Analysis of the glottal excitation of emotionally styled and stressed speech. , 1995, The Journal of the Acoustical Society of America.

[11]  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..

[12]  A. Routray,et al.  Emotion recognition from Assamese speeches using MFCC features and GMM classifier , 2008, TENCON 2008 - 2008 IEEE Region 10 Conference.

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

[14]  Richard J. Mammone,et al.  Speaker recognition using neural networks and conventional classifiers , 1994, IEEE Trans. Speech Audio Process..

[15]  D. Reynolds.  Automatic Speaker Recognition Using Gaussian Mixture Speaker Models , 1995 .

[16]  Ismail Shahin.  Improving Speaker Identification Performance Under the Shouted Talking Condition Using the Second-Order Hidden Markov Models , 2005, EURASIP J. Adv. Signal Process..

[17]  J. Oglesby,et al.  Speaker recognition using hidden Markov models, dynamic time warping and vector quantisation , 1995 .

[18]  Jianing Dai,et al.  Isolated word recognition using Markov chain models , 1995, IEEE Trans. Speech Audio Process..

[19]  John H. L. Hansen,et al.  Nonlinear feature based classification of speech under stress , 2001, IEEE Trans. Speech Audio Process..

[20]  S. Dandapat,et al.  Speaker recognition under stressed condition , 2010, Int. J. Speech Technol..

[21]  Tiago H. Falk,et al.  Modulation Spectral Features for Robust Far-Field Speaker Identification , 2010, IEEE Transactions on Audio, Speech, and Language Processing.