Voice authentication by text dependent single utterance for in-car environment
作者： Atsuki Tamoto , Katunobu Itou
关键词:
摘要: Individual authentication using speech is called speaker verification. Speaker verification, which can be implemented in portable devices, used many scenarios. This study focuses on verification while driving. Noise and long-term variability of feature are problems associated with Considering the characteristics noise a moving car, spectral subtraction cutting low frequency reduction phase. We describe adaption templates to noisy environment. also evaluate by that recorded after approximately 10 months from first enrollment.False reject rate(FRR) decreased 66.6 % average when implementing phase.In addition, FRR improved phase through an update template accepted speech.With respect variability, did not change months. result indicates GMM Posteriorgram valid for inter-speaker variability. For future study, we need consider text reduce variation GMM.
acm.org
sci-hub.se 参考文章(14)
Suman Paul Choudhury, Tushar Kanti Das, Partha Saha, Rabul Hussain, Ujwala Baruah, Comparative analysis of two different system's framework for text dependent speaker verification international conference on circuits. pp. 1- 5 ,(2015) , 10.1109/ICCPCT.2015.7159435
Lindasalwa Muda, I. Elamvazuthi, Mumtaj Begam, Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques arXiv: Multimedia. ,(2010)
Xiaojia Zhao, DeLiang Wang, Analyzing noise robustness of MFCC and GFCC features in speaker identification international conference on acoustics, speech, and signal processing. pp. 7204- 7208 ,(2013) , 10.1109/ICASSP.2013.6639061
Douglas A. Reynolds, Thomas F. Quatieri, Robert B. Dunn, Speaker Verification Using Adapted Gaussian Mixture Models Digital Signal Processing. ,vol. 10, pp. 19- 41 ,(2000) , 10.1006/DSPR.1999.0361
Ji Ming, Timothy J. Hazen, James R. Glass, Douglas A. Reynolds, Robust Speaker Recognition in Noisy Conditions IEEE Transactions on Audio, Speech, and Language Processing. ,vol. 15, pp. 1711- 1723 ,(2007) , 10.1109/TASL.2007.899278
M. Pandit, J. Kittler, Feature selection for a DTW-based speaker verification system international conference on acoustics speech and signal processing. ,vol. 2, pp. 769- 772 ,(1998) , 10.1109/ICASSP.1998.675378
Yaodong Zhang, James R. Glass, Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams ieee automatic speech recognition and understanding workshop. pp. 398- 403 ,(2009) , 10.1109/ASRU.2009.5372931
T. KAMADA, N. MINEMATSU, T. OSANAI, H. MAKINAE, M. TANIMOTO, Speaker Verification in Realistic Noisy Environment in Forensic Science The IEICE transactions on information and systems. ,vol. 91, pp. 558- 566 ,(2008) , 10.1093/IETISY/E91-D.3.558
Shi-Huang Chen, Yu-Ren Luo, Rodrigo Capobianco Guido, Speaker Verification Using Line Spectrum Frequency, Formant, and Support Vector Machine international symposium on multimedia. pp. 562- 566 ,(2009) , 10.1109/ISM.2009.132
Masatsugu Ichino, Hiroshi Yoshiura, Voiced Biometrics for Text-Indicated Speaker Recognition A - Abstracts of IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences (Japanese Edition). pp. 632- 645 ,(2015)