D-MAP: a distance-normalized MAP estimation of speaker models for automatic speaker verification

Abstract. In this paper, an automatic speaker recognition system for realistic environments is presented. In fact, most of the existing speaker recognition methods, which have shown to be highly efficient under noise free conditions, fail drastically in noisy environments. In this work, features vectors, constituted by the Mel Frequency Cepstral Coefficients (MFCC) extracted from the speech signal are used to train the Support Vector Machines (SVM) and Gaussian mixture model (GMM). To reduce the effect of noisy environments the cepstral mean subtraction (CMS) are applied on the MFCC. For both, GMM-UBM and GMM-SVM systems, 2048-mixture UBM is used. The recognition phase was tested with Arabic speakers at different Signal-to-Noise Ratio (SNR) and under three noisy conditions issued from NOISEX-92 data base. The experimental results showed that the use of appropriate kernel functions with SVM improved the global performance of the speaker recognition in noisy environments.

show abstract

“…When the GMM supervector is used, with MAP estimation [12], as input to the SVMs, the EER is 2.10%. 2.…”

Section: Speaker Recognition In Quiet Environment Using Gmm-ubm and Gmentioning

confidence: 99%

“…The GMM-UBM [2] system implemented for the purpose of this study uses MAP [12] estimation to adapt the parameters of each speaker GMM from a clean gender balanced UBM. For the purpose of consistency, a 2048-mixture UBM is used for both GMM-UBM and GMM-SVM systems.…”

Section: Gmm-ubm and Gmm-svm Systemsmentioning

confidence: 99%

Performances Evaluation of GMM-UBM and GMM-SVM for Speaker Recognition in Realistic World

Asbai

Amrouche

Debyeche

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The decrease in the objective function obtained by merging clusters and is given by (6) where is given as a combination of two Jensen-Shannon divergences (7) where denotes the Jensen-Shannon (JS) divergence between two distributions and is defined as (8) (9) with (10)…”

Section: A Agglomerative Information Bottleneckmentioning

confidence: 99%

“…Agglomerative clustering is based on similarity measures between segments. Several similarity measures have been considered in the literature based on BIC [1], modified versions of BIC [3], [4], Generalized Log-Likelihood Ratio [5], Kullback-Leibler divergence [6], or cross-likelihood distance [7]. The choice of this distance measure is somewhat arbitrary.…”

Section: Introductionmentioning

confidence: 99%

An Information Theoretic Approach to Speaker Diarization of Meeting Data

Vijayasenan

Valente

Bourlard

2009

IEEE Trans. Audio Speech Lang. Process.

116

View full text Add to dashboard Cite

Abstract-A speaker diarization system based on an information theoretic framework is described. The problem is formulated according to the Information Bottleneck (IB) principle. Unlike other approaches where the distance between speaker segments is arbitrarily introduced, the IB method seeks the partition that maximizes the mutual information between observations and variables relevant for the problem while minimizing the distortion between observations. This solves the problem of choosing the distance between speech segments, which becomes the Jensen-Shannon divergence as it arises from the IB objective function optimization. We discuss issues related to speaker diarization using this information theoretic framework such as the criteria for inferring the number of speakers, the tradeoff between quality and compression achieved by the diarization system, and the algorithms for optimizing the objective function. Furthermore, we benchmark the proposed system against a state-of-the-art system on the NIST RT06 (Rich Transcription) data set for speaker diarization of meetings. The IB-based system achieves a diarization error rate of 23.2% compared to 23.6% for the baseline system. This approach being mainly based on nonparametric clustering, it runs significantly faster than the baseline HMM/GMM based system, resulting in faster-than-real-time diarization.

show abstract

Identifying in-set and out-of-set speakers using neighborhood information

Angkititrakul

Hansen

2004 IEEE International Conference on Acoustics, Speech, and Signal Processing

View full text Add to dashboard Cite

D-MAP: a distance-normalized MAP estimation of speaker models for automatic speaker verification

Cited by 8 publications

References 4 publications

Performances Evaluation of GMM-UBM and GMM-SVM for Speaker Recognition in Realistic World

Performances Evaluation of GMM-UBM and GMM-SVM for Speaker Recognition in Realistic World

An Information Theoretic Approach to Speaker Diarization of Meeting Data

Identifying in-set and out-of-set speakers using neighborhood information

Contact Info

Product

Resources

About