Text-independent speaker recognition using non-linear frame likelihood transformation

Abstract When the reference speakers are represented by Gaussian mixture model (GMM), the conventional approach is to accumulate the frame likelihoods over the whole test utterance and compare the results as in speaker identification or apply a threshold as in speaker verification. In this paper we describe a method, where frame likelihoods are transformed into new scores according to some non-linear function prior to their accumulation. We have studied two families of such functions. First one, actually, performs likelihood normalization – a technique widely used in speaker verification, but applied here at frame level. The second kind of functions transforms the likelihoods into weights according to some criterion. We call this transformation weighting models rank (WMR). Both kinds of transformations require frame likelihoods from all (or subset of all) reference models to be available. For this, every frame of the test utterance is input to the required reference models in parallel and then the likelihood transformation is applied. The new scores are further accumulated over the whole test utterance in order to obtain an utterance level score for a given speaker model. We have found out that the normalization of these utterance scores also has the effect for speaker verification. The experiments using two databases – TIMIT corpus and NTT database for speaker recognition – showed better speaker identification rates and significant reduction of speaker verification equal error rates (EER) when the frame likelihood transformation was used.

[1]  Sadaoki Furui,et al.  Comparison of text-independent speaker recognition methods using VQ-distortion and discrete/continuous HMMs , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  I. Miller.  Probability, Random Variables, and Stochastic Processes , 1966 .

[3]  G.R. Doddington,et al.  Speaker recognition—Identifying people by their voices , 1985, Proceedings of the IEEE.

[4]  Eduardo Lleida,et al.  Efficient decoding and training procedures for utterance verification in continuous speech recognition , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[5]  Biing-Hwang Juang,et al.  A vector quantization approach to speaker recognition , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Frank K. Soong,et al.  Continuous probabilistic acoustic map for speaker identification , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  D.A. Reynolds,et al.  Large population speaker identification using clean and telephone speech , 1995, IEEE Signal Processing Letters.

[8]  Ivan Magrin-Chagnolleau,et al.  Second-order statistical measures for text-independent speaker identification , 1995, Speech Commun..

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

[10]  Biing-Hwang Juang,et al.  The use of cohort normalized scores for speaker verification , 1992, ICSLP.

[11]  S. Siegel,et al.  Nonparametric Statistics for the Behavioral Sciences , 2022, The SAGE Encyclopedia of Research Design.

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

[13]  Aaron E. Rosenberg,et al.  Connected word talker verification using whole word hidden Markov models , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[14]  H. Hartley.  Maximum Likelihood Estimation from Incomplete Data , 1958 .

[15]  Sadaoki Furui,et al.  Robust methods of updating model and a priori threshold in speaker verification , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[16]  Lawrence G. Bahler,et al.  Speaker verification using randomized phrase prompting , 1991, Digit. Signal Process..

[17]  Sadaoki Furui,et al.  Concatenated phoneme models for text-variable speaker recognition , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[18]  Naftali Z. Tisby.  On the application of mixture AR hidden Markov models to text independent speaker recognition , 1991, IEEE Trans. Signal Process..

[19]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[20]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[21]  R. Okafor.  Maximum likelihood estimation from incomplete data , 1987 .

[22]  Seiichi Nakagawa,et al.  Frame level likelihood normalization for text-independent speaker identification using Gaussian mixture models , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[23]  Aaron E. Rosenberg,et al.  Cepstral channel normalization techniques for HMM-based speaker verification , 1994, ICSLP.

[24]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[25]  Aaron E. Rosenberg,et al.  Report: A vector quantization approach to speaker recognition , 1987, AT&T Technical Journal.

[26]  H. Gish,et al.  Text-independent speaker identification , 1994, IEEE Signal Processing Magazine.

[27]  Seiichi Nakagawa,et al.  TEXT-INDEPENDENT SPEAKER IDENTIFICATION ON TIMIT DATABASE , 1995 .

[28]  Douglas A. Reynolds,et al.  Speaker identification and verification using Gaussian mixture speaker models , 1995, Speech Commun..

[29]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[30]  Sadaoki Furui,et al.  Likelihood normalization for speaker verification using a phoneme- and speaker-independent model , 1995, Speech Commun..

[31]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[32]  M. Savic,et al.  Variable parameter speaker verification system based on hidden Markov modeling , 1990, International Conference on Acoustics, Speech, and Signal Processing.