Generalizing I-Vector Estimation for Rapid Speaker Recognition

Xu, Longting; Lee, Kong Aik; Li, Haizhou; Yang, Zhen

doi:10.1109/taslp.2018.2793670

Cited by 17 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The framework of a speaker recognition system based i-vector is shown in Figure 1. The main problems that need to be processed are finding the full variable space T, and extracting the i-vector, and channel compensation as well as cosine distance scoring [15].…”

Section: The Principle Of I-vectormentioning

confidence: 99%

Text independent voiceprint recognition model based on I-vector

Zhang¹,

Yao²

2020

IJATEE

View full text Add to dashboard Cite

Speaker Recognition is a technology for identifying people based on the Voiceprint characteristics contained in voice, and is a kind of biometric authentication technology. According to different recognition methods, Voiceprint recognition can be divided into three categories [1]. (1) Speaker discrimination is to distinguish who is talking from a given speaker set; (2) speaker confirmation is to judge whether someone is speaking or not; (3) speaker segmenting and clustering is to distinguish the switching time of different speakers based on the voice formed by multiple speakers.

show abstract

Section: The Principle Of I-vectormentioning

confidence: 99%

Text independent voiceprint recognition model based on I-vector

Zhang¹,

Yao²

2020

IJATEE

View full text Add to dashboard Cite

show abstract

“…This will lead to the decline of system performance. In order to solve this problem, we utilized WCCN 23 to restrain noise and channel distortion in kernel function space. The covariance matrix of single speaker only reflects the influence of noise.…”

Section: Svm Kernel Based On Bhattacharyya Distance Clustering and Wccnmentioning

confidence: 99%

Speaker verification normalization sequence kernel based on Gaussian mixture model super-vector and Bhattacharyya distance

Xing

Tan

Wang

2019

Journal of Low Frequency Noise, Vibration and Active Control

View full text Add to dashboard Cite

Due to the accessibility and economy of human speech, speaker verification has become the research hotspot in the field of biometric authentication. A novel normalization sequence kernel based on Bhattacharyya distance clustering and within class covariance normalization was proposed in this paper. In this kernel, the high computation complexity and channel interference susceptibility that commonly exist in speaker verification could be restrained. In our method, we calculated the Bhattacharyya distance between pairs of Gaussian mixture models first. And then, a clustering algorithm was designed according to Gaussian mixture model’s Bhattacharyya distance to obtain clustering center models. Maximum a posteriori was applied on these clustering center models to generate super-vectors immediately following. The sequence kernel was generated based on Bhattacharyya distance transformation and super-vectors. Finally, within class covariance normalization was utilized to restrain the channel distortion in kernel space. We adopted support vector machine as classifier to decide the target speaker. The experiment results on TIMIT corpus and NIST 2008 SRE showed that our proposed kernel has superior recognition accuracy and better robustness.

show abstract

“…A speaker dependent supervector is formed by using the acoustic features from all of the speaker's training utterances. Note that with SPPCA, h should be used instead of s in (9) and that Q's dimensionality is the same as V 's.…”

Section: I-vector Extractionmentioning

confidence: 99%

“…Previous studies on rapid i-vector extraction have primarily optimized computations in the standard front-end factor analysis (FEFA) approach [1,2] by adopting new computational algorithms, often approximative in nature [6,8,9]. In this study, however, we focus on an alternative and straightforward compression of classic maximum a posteriori (MAP) [3] adapted GMM supervectors with a goal of obtaining fast execution times without compromising on ASV accuracy.…”

Section: Introductionmentioning

confidence: 99%

Supervector Compression Strategies to Speed up I-Vector System Development

Vestman¹,

Kinnunen²

2018

The Speaker and Language Recognition Workshop (Odyssey 2018)

View full text Add to dashboard Cite

The front-end factor analysis (FEFA), an extension of principal component analysis (PPCA) tailored to be used with Gaussian mixture models (GMMs), is currently the prevalent approach to extract compact utterance-level features (i-vectors) for automatic speaker verification (ASV) systems. Little research has been conducted comparing FEFA to the conventional PPCA applied to maximum a posteriori (MAP) adapted GMM supervectors. We study several alternative methods, including PPCA, factor analysis (FA), and two supervised approaches, supervised PPCA (SPPCA) and the recently proposed probabilistic partial least squares (PPLS), to compress MAP-adapted GMM supervectors. The resulting i-vectors are used in ASV tasks with a probabilistic linear discriminant analysis (PLDA) back-end. We experiment on two different datasets, on the telephone condition of NIST SRE 2010 and on the recent VoxCeleb corpus collected from YouTube videos containing celebrity interviews recorded in various acoustical and technical conditions. The results suggest that, in terms of ASV accuracy, the supervector compression approaches are on a par with FEFA. The supervised approaches did not result in improved performance. In comparison to FEFA, we obtained more than hundred-fold (100x) speedups in the total variability model (TVM) training using the PPCA and FA supervector compression approaches.

show abstract

Generalizing I-Vector Estimation for Rapid Speaker Recognition

Cited by 17 publications

References 27 publications

Text independent voiceprint recognition model based on I-vector

Text independent voiceprint recognition model based on I-vector

Speaker verification normalization sequence kernel based on Gaussian mixture model super-vector and Bhattacharyya distance

Supervector Compression Strategies to Speed up I-Vector System Development

Contact Info

Product

Resources

About