Buradasınız

KONUŞMACI TANIMA İÇİN ÖZELLİK SEÇİMİ VE SINIFLANDIRMA TEKNİKLERİ

FEATURE SELECTION AND CLASSIFICATION TECHNIQUES FOR SPEAKER RECOGNITION

Journal Name:

Publication Year:

Keywords (Original Language):

Author NameUniversity of AuthorFaculty of Author
Abstract (2. Language): 
Speaker recognition can be considered as a subset of the more general area known as pattern recognition, which may be viewed basically in three stages as: feature selection and extraction, classification, and pattern matching. Extensive research in the past has been directed towards finding effective speech characteristics for speaker recognition. But, so far, no feature set is found to be known to allow perfect discrimination for all conditions. As the performance of features depends on the nature of application, the selection of salient features is a key step in the recognition process. In this paper, we present a general view of speech features and well known classifiers originally developed for text-independent speaker recognition systems. A comparative discussion on choice of suitable speech features and classification techniques is also given.
Abstract (Original Language): 
Konuşmacı tanıma; özellik seçip elde etme, sınıflandırma ve örüntü karşılaştırma olarak üç aşamadan oluşan örüntü tanıma olarak bilinen genel bir alanın, bir alt kümesi olarak düşünülebilir. Geçmişten bu yana, konuşmacı tanımaya elverişli ses karakteristiklerinin bulunması yönünde yoğun çalışmalar yapılmış olmasına rağmen, henüz tüm şartlar için mükemmel ayırt etmeye yarayan bir özellik kümesi bulunamamıştır. Dolayısı ile, özelliklerin sistem başarımına etkisi uygulamanın tipine bağlı olduğundan, has özelliklerin seçimi tanıma işleminin en önemli basamağını oluşturmaktadır. Bu makalede, ses özellikleri ve daha çok metinden bağımsız konuşmacı tanıma için geliştirilmiş en çok bilinen sınıflandırma tekniklerine genel bir bakış verilmiştir. Ayrıca, uygun ses özellikleri ve sınıflayıcıların seçimleri karşılaştırmalı olarak tartışılmıştır.

REFERENCES

References: 

Assaleh, K. T. and Mammone, R. J. 1994. New LP-Derived Features for Speaker Identification.
IEEE SAP, Vol. SAP-2, No. 4, 630-638.
Atal, B. S. 1972. Automatic Speaker Recognition
Based on Pitch Contours. JASA, 52, 1687-1697.
Atal, B. S. 1974. Effectiveness of Linear Prediction Characteristics of the Speech Wave for Automatic Speaker Identification and Verification. JASA,
55, 6, 1304-1312.
Bennani, Y. and Gallinari, P. 1991. On the use of TDNN-Extracted Features Information in Talker
Identification. IEEE Proc. ICASSP"91. 265-268.
Bennani, Y. and Gallinari, P. 1994. Connectionist Approaches for Automatic Speaker Recognition. Proc. ESCA Workshop. 95-102.
Broad, D. J. 1972. Formants in Automatic Speech Recognition. Int. J. Man-Machine Studies, 4, 411.
Campbell, J.P. 1997. Speaker Recognition: A
Tutorial. Proc. IEEE, Vol. 85, No. 9, Sept. 1997, 1437-1462.
Das, S. K. and Mohn, W. S. 1971. A Scheme for
Speech Processing in Automatic Speaker Verification. IEEE Trans. Audio and Electroacoustics, AU-19, 32-43.
Davis, S. B. and Mermelstein, P. 1980. Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken
Sentences. IEEE ASSP-28. 357-366.
Farrell, K. R. Mammone, R. J. and Assaleh, K. T. 1994. Speaker Recognition Using Neural Networks
and Conventional Classifiers. IEEE SAP, Vol. SAP-
2, No. 1, Pt. 2, 194-205.
Furui, S. 1981. Cepstral Analysis Technique for
Automatic Speaker Verification. IEEE ASSP-29, No. 2, 254-272.
Gopalan, K., Anderson, T.R. and Cupples, E. J. 1999. A Comparison of Speaker Identification Results Using Features Based on Cepstrum and Fourier-Bessel Expansion. IEEE SAP, Vol. SAP-7,
No. 3, 289-294.
Mühendislik
Bilimler
i Dergisi 2001 7 (1) 47-54
52
Journal of Engineering Sciences 2001 7 (1) 47-54
Feature Selection and Classification Techniques for Speaker Recognition, F. Ertaş
Table 1. Summary of Speaker Identification (SI) and Speaker Verification (SV) Studies
Mühendislik
Bilimler
i Dergisi 2001 7 (1) 47-54
53
Journal of Engineering Sciences 2001 7 (1) 47-54
Feature Selection and Classification Techniques for Speaker Recognition, F. Ertaş
Haydar, A., Demirekler, M. and Yurtseven, M. K.
1998
. Speaker Identification Through Use of Features Selected Using Genetic Algorithm. Electronics Letters, 34 (1), 39-40.
Le Floch, J. L., Montacie, C. and Caraty, M. J.
1995. Speaker Recognition Experiments on the TIMIT Database. Proc. ESCA Workshop. 379-382.
Lewis, D. and Tuthill, C. 1940. Resonant
Frequencies and Damping Constants of Resonators Involved in the Production of Sustained Vowel 'O' and 'Ah'. JASA, 11, 451.
Liu, C. S., Wang, H. C. and Lee, C. H. 1996.
Speaker Verification Using Normalized Log-likelihood Score. IEEE SAP, Vol. SAP-4, No. 1, 56-59.
Makhoul, J. 1975. Linear Prediction: A Tutorial
Review. Proc. IEEE, Vol. 63, 561-580.
Mammone, R. J., Zhang, X. and Ramachandran, R.
1996. Robust Speaker Recognition: A Feature-Based Approach. IEEE Signal Proc. Mag. 58-71.
Matsui, T. and Furui, S. 1991. A Text-Independent Speaker Recognition Method Robust Against
Utterance Variations. IEEE Proc. ICASSP'91. 377-380.
Matsui, T. and Furui, S. 1994. Comparison of Text-Independent Speaker Recognition Methods Using VQ-Distortion and Discrete/Continuous HMM's.
IEEE SAP, Vol. SAP-2, No. 3, 456-458.
Murthy, H. A., Beaufays, F., Heck, L.P. and Weintraub, M. 1999. Robust Text-Independent Speaker Identification Over Telephone Channels.
IEEE SAP, Vol. SAP-7, No. 5, 554-568.
Oglesby, J. and Mason, J. S. 1990. Optimization and Neural Models for Speaker Identification. IEEE
Proc. ICASSP'90. 261-264.
Oglesby, J. and Mason, J. S. 1991. Radial Basis Function Networks for Speaker Recognition. Proc. ESCA Workshop. 87-90.
O'Shaughnessy, D. 1986. Speaker Recognition. IEEE ASSP Magazine. 4-17.
Poritz, A.B. 1982. Linear Predictive hidden Markov Models and the Speech Signal. IEEE Proc. ICASSP"82. 1291-1294.
Ren-hua, W., Lin-shen, H. and Fujisaki, H. 1990. A Weighted Distance Measure Based on the Fine Structure of Feature Space: Application to Speaker
Recognition. IEEE Proc. ICASSP'90. 273-276.
Reynolds, D. A. and Heck, L. P. 1991. Integration of Speaker and Speech Recognition Systems. IEEE
Proc. ICASSP"91. 869-872.
Reynolds, D. A. 1992. A Gaussian Mixture Modeling Approach to Text-Independent Speaker Identification. PhD. Thesis. Georgia Ins. of Tech.
Reynolds, D. A. and Carlson, B. 1995. Text-Independent Speaker Verification Using Decoupled and Integrated Speaker and Speech Recognizers.
Proc. EUROSPEECH. 647-650.
Reynolds, D. A. and Rose, R.C. 1995. Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models. IEEE SAP-3, No.1, 72¬83.
Rose, R. C. and Reynolds, D. A. 1990. Text-Independent Speaker Identification Using Automatic Acoustic Segmentation. IEEE Proc.
ICASSP'90. 293-296.
Rose, R. C., Hofstetter, E.M. and Reynolds, D. A. 1994. Integrated Models of Speech and Background With Application to Speaker Identification in
Noise. IEEE SAP-2. No. 2. 245-257.
Rosenberg, A. E. and Soong, F. K. 1987. Evaluation of a Vector Quantization Talker Recognition System in Text-independent and text-dependent modes. Computer Speech and Language.
143-157.
Rosenberg, A.E., Lee, C.-H. and Gokcen, S. 1991. Connected Word Talker Verification Using Whole Word HMMs. IEEE Proc. ICASSP'91, 381-384.
Rudasi, L. and Zahorian, S. A. 1991. Text-Independent Talker Identification With Neural
Networks. IEEE Proc. ICASSP"91. 389-392. Savic, M. and Gupta, S. K. 1990. Variable
Parameter Speaker Verification System Based on
Hidden Markov Modeling. IEEE Proc. ICASSP"90. 281-284.
Soong, F. K., Rosenberg, A.E., Rabiner, L. R. and Juang, B. H. 1985. A Vector Quantization Approach to Speaker Recognition. IEEE Proc. ICASSP'85, Tamoa, FL, 387-390.
Sukkar, R. A., Gandhi, M. B. and Setlur, A. R.
2000. Speaker Verification Using Mixture Decomposition discrimination. IEEE SAP, Vol.
SAP-8, No. 3, 292-299.
Tierney, J. 1980. A study of LPC Analysis of Speech in Additive Noise. IEEE ASSP-28. 389¬397.
Tishby, N. Z. 1991. On the Application of Mixture AR Hidden Markov Models to Text-Independent Speaker Recognition. IEEE ASSP-39. 563-570.
Yuan, Z. X., Xu, B. L. and Yu, C. Z. 1999. Binary Quantization of Feature Vectors for Robust Text-Independent Speaker Identification. IEEE SAP,
Vol. SAP-6, No. 1, 70-78.
Zhang, Y., Zhu, X. and Zhang, D. 1999. Speaker Verification by Removing Common Information.
Electronics Letters, 35 (23), 2009-2011.

Thank you for copying data from http://www.arastirmax.com