scholarly journals Towards an Optimal Speaker Modeling in Speaker Verification Systems using Personalized Background Models

2017 ◽  
Vol 7 (6) ◽  
pp. 3655
Author(s):  
Ayoub Bouziane ◽  
Jamal Kharroubi ◽  
Arsalane Zarghili
Keyword(s):  
Speaker Recognition ◽  
Speaker Verification ◽  
Computational Cost ◽  
Verification Task ◽  
Speech Data ◽  
Recognition Systems ◽  
Verification Systems ◽  
Background Models ◽  
Target Speaker ◽  
Speaker Modeling

<p>This paper presents a novel speaker modeling approachfor speaker recognition systems. The basic idea of this approach consists of deriving the target speaker model from a personalized background model, composed only of the UBM Gaussian components which are really present in the speech of the target speaker. The motivation behind the derivation of speakers’ models from personalized background models is to exploit the observeddifference insome acoustic-classes between speakers, in order to improve the performance of speaker recognition systems.</p>The proposed approach was evaluatedfor speaker verification task using various amounts of training and testing speech data. The experimental results showed that the proposed approach is efficientin termsof both verification performance and computational cost during the testing phase of the system, compared to the traditional UBM based speaker recognition systems.

SVM AGAINST GMM/SVM FOR DIALECT INFLUENCE ON AUTOMATIC SPEAKER RECOGNITION TASK

2014 ◽  
Vol 13 (02) ◽  
pp. 1450012 ◽  
Author(s):  
KAWTHAR YASMINE ZERGAT ◽  
ABDERRAHMANE AMROUCHE
Keyword(s):  
Speaker Recognition ◽  
Speaker Verification ◽  
Recognition Task ◽  
Principal Component ◽  
Recognition System ◽  
Automatic Speaker Recognition ◽  
Modeling Techniques ◽  
Recognition Systems ◽  
Speaking Style ◽  
Speaker Modeling

A big deal for current research on automatic speaker recognition is the effectiveness of the speaker modeling techniques for the talkers, because they have their own speaking style, depending on their specific accents and dialects. This paper investigates on the influence of the dialect and the size of database on the text independent speaker verification task using the SVM and the hybrid GMM/SVM speaker modeling. The Principal Component Analysis (PCA) technique is used in the front-end part of the speaker recognition system, in order to extract the most representative features. Experimental results show that the size of database has an important impact on the SVM and GMM/SVM based speaker verification performances, while the dialect has no significant effect. Applying PCA dimensionality reduction improves the recognition accuracy for both SVM and GMM/SVM based recognition systems. However, it did not give an obvious observation about the dialect effect.

scholarly journals Speaker Model Clustering to Construct Background Models for Speaker Verification

2017 ◽  
Vol 42 (1) ◽  
pp. 127-135
Author(s):  
Gökay Dişken ◽  
Zekeriya Tüfekci ◽  
Ulus Çevik
Keyword(s):  
Speaker Recognition ◽  
Distance Measure ◽  
Speaker Verification ◽  
Statistical Significance ◽  
Error Rates ◽  
Vector Method ◽  
Channel Mismatch ◽  
Euclidean Distance Measure ◽  
Recognition Systems ◽  
Background Models

Abstract Conventional speaker recognition systems use the Universal Background Model (UBM) as an imposter for all speakers. In this paper, speaker models are clustered to obtain better imposter model representations for speaker verification purpose. First, a UBM is trained, and speaker models are adapted from the UBM. Then, the k-means algorithm with the Euclidean distance measure is applied to the speaker models. The speakers are divided into two, three, four, and five clusters. The resulting cluster centers are used as background models of their respective speakers. Experiments showed that the proposed method consistently produced lower Equal Error Rates (EER) than the conventional UBM approach for 3, 10, and 30 seconds long test utterances, and also for channel mismatch conditions. The proposed method is also compared with the i-vector approach. The three-cluster model achieved the best performance with a 12.4% relative EER reduction in average, compared to the i-vector method. Statistical significance of the results are also given.

Robustness Speaker Recognition Based on Feature Space in Clean and Noisy Condition

2019 ◽  
Vol 9 (4) ◽  
pp. 497-506 ◽  
Author(s):  
Khamis A. Al-Karawi
Keyword(s):  
Speech Processing ◽  
Speaker Recognition ◽  
System Performance ◽  
Speaker Verification ◽  
Signal To Noise Ratio ◽  
Recognition Performance ◽  
Feature Space ◽  
Signal To Noise ◽  
Verification Systems ◽  
Noisy Condition

Background & Objective: Speaker Recognition (SR) techniques have been developed into a relatively mature status over the past few decades through development work. Existing methods typically use robust features extracted from clean speech signals, and therefore in idealized conditions can achieve very high recognition accuracy. For critical applications, such as security and forensics, robustness and reliability of the system are crucial. Methods: The background noise and reverberation as often occur in many real-world applications are known to compromise recognition performance. To improve the performance of speaker verification systems, an effective and robust technique is proposed to extract features for speech processing, capable of operating in the clean and noisy condition. Mel Frequency Cepstrum Coefficients (MFCCs) and Gammatone Frequency Cepstral Coefficients (GFCC) are the mature techniques and the most common features, which are used for speaker recognition. MFCCs are calculated from the log energies in frequency bands distributed over a mel scale. While GFCC has been acquired from a bank of Gammatone filters, which was originally suggested to model human cochlear filtering. This paper investigates the performance of GFCC and the conventional MFCC feature in clean and noisy conditions. The effects of the Signal-to-Noise Ratio (SNR) and language mismatch on the system performance have been taken into account in this work. Conclusion: Experimental results have shown significant improvement in system performance in terms of reduced equal error rate and detection error trade-off. Performance in terms of recognition rates under various types of noise, various Signal-to-Noise Ratios (SNRs) was quantified via simulation. Results of the study are also presented and discussed.

Speaker Verification and Identification

2010 ◽  
pp. 264-289
Author(s):  
Minho Jin ◽  
Chang D. Yoo
Keyword(s):  
Feature Extraction ◽  
Speaker Recognition ◽  
Speaker Identification ◽  
Speaker Verification ◽  
Gaussian Mixture ◽  
Recognition System ◽  
Essential Elements ◽  
Verification System ◽  
Biometric Characteristic ◽  
Speaker Modeling

A speaker recognition system verifies or identifies a speaker’s identity based on his/her voice. It is considered as one of the most convenient biometric characteristic for human machine communication. This chapter introduces several speaker recognition systems and examines their performances under various conditions. Speaker recognition can be classified into either speaker verification or speaker identification. Speaker verification aims to verify whether an input speech corresponds to a claimed identity, and speaker identification aims to identify an input speech by selecting one model from a set of enrolled speaker models. Both the speaker verification and identification system consist of three essential elements: feature extraction, speaker modeling, and matching. The feature extraction pertains to extracting essential features from an input speech for speaker recognition. The speaker modeling pertains to probabilistically modeling the feature of the enrolled speakers. The matching pertains to matching the input feature to various speaker models. Speaker modeling techniques including Gaussian mixture model (GMM), hidden Markov model (HMM), and phone n-grams are presented, and in this chapter, their performances are compared under various tasks. Several verification and identification experimental results presented in this chapter indicate that speaker recognition performances are highly dependent on the acoustical environment. A comparative study between human listeners and an automatic speaker verification system is presented, and it indicates that an automatic speaker verification system can outperform human listeners. The applications of speaker recognition are summarized, and finally various obstacles that must be overcome are discussed.

Building Sequence Kernels for Speaker Verification and Word Recognition

2011 ◽  
pp. 575-589
Author(s):  
Vincent Wan
Keyword(s):  
Speech Recognition ◽  
Speech Processing ◽  
Kernel Methods ◽  
Speaker Recognition ◽  
Dynamic Time Warping ◽  
Speaker Verification ◽  
Dimensional Space ◽  
Time Warping ◽  
Recognition Systems ◽  
Dynamic Time

This chapter describes the adaptation and application of kernel methods for speech processing. It is divided into two sections dealing with speaker verification and isolated-word speech recognition applications. Significant advances in kernel methods have been realised in the field of speaker verification, particularly relating to the direct scoring of variable-length speech utterances by sequence kernel SVMs. The improvements are so substantial that most state-of-the-art speaker recognition systems now incorporate SVMs. We describe the architecture of some of these sequence kernels. Speech recognition presents additional challenges to kernel methods and their application in this area is not as straightforward as for speaker verification. We describe a sequence kernel that uses dynamic time warping to capture temporal information within the kernel directly. The formulation also extends the standard dynamic time-warping algorithm by enabling the dynamic alignment to be computed in a high-dimensional space induced by a kernel function. This kernel is shown to work well in an application for recognising low-intelligibility speech of severely dysarthric individuals.

Building Sequence Kernels for Speaker Verification and Word Recognition

2011 ◽  
pp. 246-262
Author(s):  
Vincent Wan
Keyword(s):  
Speech Recognition ◽  
Speech Processing ◽  
Kernel Methods ◽  
Speaker Recognition ◽  
Dynamic Time Warping ◽  
Speaker Verification ◽  
Dimensional Space ◽  
Time Warping ◽  
Recognition Systems ◽  
Dynamic Time

This chapter describes the adaptation and application of kernel methods for speech processing. It is divided into two sections dealing with speaker verification and isolated-word speech recognition applications. Significant advances in kernel methods have been realised in the field of speaker verification, particularly relating to the direct scoring of variable-length speech utterances by sequence kernel SVMs. The improvements are so substantial that most state-of-the-art speaker recognition systems now incorporate SVMs. We describe the architecture of some of these sequence kernels. Speech recognition presents additional challenges to kernel methods and their application in this area is not as straightforward as for speaker verification. We describe a sequence kernel that uses dynamic time warping to capture temporal information within the kernel directly. The formulation also extends the standard dynamic time-warping algorithm by enabling the dynamic alignment to be computed in a high-dimensional space induced by a kernel function. This kernel is shown to work well in an application for recognising low-intelligibility speech of severely dysarthric individuals.

scholarly journals Introducing phonetic information to speaker embedding for speaker verification

2019 ◽  
Vol 2019 (1) ◽  
Author(s):  
Yi Liu ◽  
Liang He ◽  
Jia Liu ◽  
Michael T. Johnson
Keyword(s):  
Speech Processing ◽  
Speaker Recognition ◽  
Speaker Verification ◽  
Vector System ◽  
Equal Error Rate ◽  
Phonetic Information ◽  
Essential Components ◽  
Verification Systems ◽  
Vector Architectures ◽  
Vector Approach

AbstractPhonetic information is one of the most essential components of a speech signal, playing an important role for many speech processing tasks. However, it is difficult to integrate phonetic information into speaker verification systems since it occurs primarily at the frame level while speaker characteristics typically reside at the segment level. In deep neural network-based speaker verification, existing methods only apply phonetic information to the frame-wise trained speaker embeddings. To improve this weakness, this paper proposes phonetic adaptation and hybrid multi-task learning and further combines these into c-vector and simplified c-vector architectures. Experiments on National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) 2010 show that the four proposed speaker embeddings achieve better performance than the baseline. The c-vector system performs the best, providing over 30% and 15% relative improvements in equal error rate (EER) for the core-extended and 10 s–10 s conditions, respectively. On the NIST SRE 2016, 2018, and VoxCeleb datasets, the proposed c-vector approach improves the performance even when there is a language mismatch within the training sets or between the training and evaluation sets. Extensive experimental results demonstrate the effectiveness and robustness of the proposed methods.

scholarly journals Towards an objective comparison of feature extraction techniques for automatic speaker recognition systems

2021 ◽  
Vol 10 (1) ◽  
pp. 374-382
Author(s):  
Ayoub Bouziane ◽  
Jamal Kharroubi ◽  
Arsalane Zarghili
Keyword(s):  
Feature Extraction ◽  
Speaker Recognition ◽  
Comparative Studies ◽  
Features Extraction ◽  
Modeling Technique ◽  
Extraction Techniques ◽  
Automatic Speaker Recognition ◽  
Recognition Systems ◽  
Speaker Modeling

A common limitation of the previous comparative studies on speaker-features extraction techniques lies in the fact that the comparison is done independently of the used speaker modeling technique and its parameters. The aim of the present paper is twofold. Firstly, it aims to review the most significant advancements in feature extraction techniques used for automatic speaker recognition. Secondly, it seeks to evaluate and compare the currently dominant ones using an objective comparison methodology that overcomes the various limitations and drawbacks of the previous comparative studies. The results of the carried out experiments underlines the importance of the proposed comparison methodology. 

STC-Innovation Speaker Recognition Systems for Far-Field Speaker Verification Challenge 2020

2020 ◽  
Author(s):  
Aleksei Gusev ◽  
Vladimir Volokhov ◽  
Alisa Vinogradova ◽  
Tseren Andzhukaev ◽  
Andrey Shulipa ◽  
...  
Keyword(s):  
Speaker Recognition ◽  
Speaker Verification ◽  
Far Field ◽  
Recognition Systems

scholarly journals A simulation study on optimal scores for speaker recognition

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Dong Wang
Keyword(s):  
Simulation Study ◽  
Speaker Recognition ◽  
Speaker Identification ◽  
Speaker Verification ◽  
Real Life ◽  
Recognition System ◽  
Single Form ◽  
Recognition Systems ◽  
Minimum Bayes Risk ◽  
Cosine Distance

AbstractIn this article, we conduct a comprehensive simulation study for the optimal scores of speaker recognition systems that are based on speaker embedding. For that purpose, we first revisit the optimal scores for the speaker identification (SI) task and the speaker verification (SV) task in the sense of minimum Bayes risk (MBR) and show that the optimal scores for the two tasks can be formulated as a single form of normalized likelihood (NL). We show that when the underlying model is linear Gaussian, the NL score is mathematically equivalent to the PLDA likelihood ratio (LR), and the empirical scores based on cosine distance and Euclidean distance can be seen as approximations of this linear Gaussian NL score under some conditions.Based on the unified NL score, we conducted a comprehensive simulation study to investigate the behavior of the scoring component on both the SI task and SV task, in the case where the distribution of the speaker vectors perfectly matches the assumption of the NL model, as well as the case where some mismatch is involved. Importantly, our simulation is based on the statistics of speaker vectors derived from a practical speaker recognition system, hence reflecting the behavior of the NL scoring in real-life scenarios that are full of imperfection, including non-Gaussianality, non-homogeneity, and domain/condition mismatch.

Sign in / Sign up

Export Citation Format

Share Document