A Study of Interspeaker Variability in Speaker Verification

Kenny, Patrick; Ouellet, Pierre; Dehak, Najim; Gupta, Vishwa; Dumouchel, Pierre

doi:10.1109/tasl.2008.925147

Cited by 532 publications

(375 citation statements)

References 26 publications

Supporting

Mentioning

369

Contrasting

Unclassified

Order By: Relevance

“…The i-vectors are also length-normalised [7]. Details about training of total variability space matrix T can be seen in [13] or [14]. Because of the differences between each conversation (and the similarity in one conversation), we also compute a conversation dependent PCA transformation, which further reduces the dimensionality of the i-vector w. The dimension of the PCA latent space is dependent on the parameter p, the ratio of eigenvalue mass [8] (in our case p = 0.5).…”

Section: I-vectorsmentioning

confidence: 99%

Investigation of Segmentation in i-Vector Based Speaker Diarization of Telephone Speech

Zajíc

Kunešová

Radová

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The goal of this paper is to evaluate the contribution of speaker change detection (SCD) to the performance of a speaker diarization system in the telephone domain. We compare the overall performance of an i-vector based system using both SCD-based segmentation and a naive constant length segmentation with overlapping segments. The diarization system performs K-means clustering of i-vectors which represent the individual segments, followed by a resegmentation step. Experiments were done on the English part of the CallHome corpus. The final results indicate that the use of speaker change detection is beneficial, but the differences between the two segmentation approaches are diminished by the use of resegmentation.

show abstract

Section: I-vectorsmentioning

confidence: 99%

Investigation of Segmentation in i-Vector Based Speaker Diarization of Telephone Speech

Zajíc

Kunešová

Radová

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Kenny [13] provides a more detailed explanation of the derivation of these parameters, using the EM algorithm.…”

Section: I-vector Extractionmentioning

confidence: 99%

“…The i-vector is a compact representation (typically from 400 to 600 dimensions) of a whole utterance, derived as a point estimate of the latent variables in a factor analysis model [12] [13]. However, while proven to be successful in a variety of scenarios, i-vector based approaches suffer from two major drawbacks when coping with real-time applications.…”

Section: Introductionmentioning

confidence: 99%

Frame-by-frame language identification in short utterances using deep neural networks

et al. 2015

View full text Add to dashboard Cite

Esta es la versión de autor del artículo publicado en: This is an author produced version of a paper published in:Neural Networks 64 (2015) AbstractThis work addresses the use of deep neural networks (DNNs) in automatic language identification (LID) focused on short test utterances. Motivated by their recent success in acoustic modelling for speech recognition, we adapt DNNs to the problem of identifying the language in a given utterance from the short-term acoustic features. We show how DNNs are particularly suitable to perform LID in real-time applications, due to their capacity to emit a language identification posterior at each new frame of the test utterance. We then analyse different aspects of the system, such as the amount of required training data, the number of hidden layers, the relevance of contextual information and the effect of the test utterance duration. Finally, we propose several methods to combine frame-by-frame posteriors. Experiments are conducted on two different datasets: the public NIST Language Recognition Evaluation 2009 (3 seconds task) and a much larger corpus (of 5 million utterances) known as Google 5M LID, obtained from different Google Services. Reported results show relative improvements of DNNs versus the i-vector system of 40% in LRE09 3 second task and 76% in Google 5M LID.

show abstract

“…Factor analysis has led to the development of an effective method of compensating for intersession variability in speaker verification. Joint Factor Analysis (JFA) [3], [4] and total variability factor analysis [5], [6] have been successfully applied in speaker verification.…”

Section: Introductionmentioning

confidence: 99%

“…The techniques of intersession compensation of LDA and WCCN are briefly introduced in Sect. 4. Experiments and results are presented in Sect.…”

Section: Introductionmentioning

confidence: 99%

Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification

Chen

Yang

Zhao

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this letter, we adopt a new factor analysis of neighborhood-preserving embedding (NPE) for speaker verification. NPE aims at preserving the local neighborhood structure on the data and defines a low-dimensional speaker space called neighborhood-preserving embedding space. We compare the proposed method with the state-of-the-art total variability approach on the telephone-telephone core condition of the NIST 2008 Speaker Recognition Evaluation (SRE) dataset. The experimental results indicate that the proposed NPE method outperforms the total variability approach, providing up to 24% relative improvement.

show abstract

A Study of Interspeaker Variability in Speaker Verification

Cited by 532 publications

References 26 publications

Investigation of Segmentation in i-Vector Based Speaker Diarization of Telephone Speech

Investigation of Segmentation in i-Vector Based Speaker Diarization of Telephone Speech

Frame-by-frame language identification in short utterances using deep neural networks

Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification

Contact Info

Product

Resources

About