A Unified Joint Model to Deal With Nuisance Variabilities in the i-Vector Space

Kheder, Waad Ben; Matrouf, Driss; Ajili, Moez; Bonastre, Jean-François

doi:10.1109/taslp.2018.2789399

Cited by 10 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Thanks to its statistical properties, developing denoising techniques in modeling level is more promising and easier than signal or feature level. The relative improvement of EER, in signal level [7], shows that results obtained in speaker modeling level are better than signal or feature level [4].…”

Section: Related Workmentioning

confidence: 99%

“…The main advantage of this method is that it uses both information about the relation between noisy and clean speech and the clean speech distribution [5]. A nonparametric algorithm without considering the relation between corrupted and clean i-vector was proposed by [4], that utilizes the joint distribution of corrupted and clean i-vectors to denoise corrupted i-vector with an MMSE estimator. Neural autoencoders for denoising i-vectors have also been investigated in [13] and in [14] a classifier is jointly trained with a DAE in order to make the new i-vector more discriminative.…”

Section: Related Workmentioning

confidence: 99%

“…Applying denoising techniques at the speaker modeling level has been done successfully in the i-vector space [4,5,6]. In this paper we apply statistical denoising techniques on xvectors that works effectively in i-vector domain.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Denoising x-vectors for Robust Speaker Recognition

Mohammadamini

Matrouf

Noé

2020

The Speaker and Language Recognition Workshop (Odyssey 2020)

Self Cite

View full text Add to dashboard Cite

Using deep learning methods has led to significant improvement in speaker recognition systems. Introducing xvectors as a speaker modeling method has made these systems more robust. Since, in challenging environments with noise and reverberation, the performance of x-vectors systems degrades significantly, the demand for denoising techniques remains as before. In this paper, for the first time, we try to denoise the xvectors speaker embedding. Our focus is on additive noise. Firstly, we use the i-MAP method which considers that both noise and clean x-vectors have a Gaussian distribution. Then, leveraging denoising autoencoders (DAE) we try to reconstruct the clean x-vector from the corrupted version. After that, we propose two hybrid systems composed of statistical i-MAP and DAE. Finally, we propose a novel DAE architecture, named Deep Stacked DAE, composed of several DAEs where each DAE receives as input the output of its predecessor DAE concatenated with the difference between noisy x-vectors and its predecessor's output. The experiments on Fabiol corpus show that the results given by the hybrid DAE i-MAP method in several cases outperforms the conventional DAE and i-MAP methods. Also, the results for Deep Stacked DAE in most cases is better than the other proposed methods. For utterances longer than 12 seconds we achieved a 51% improvement in terms of EER with Deep Stacked DAE, and for utterances shorter than 2 seconds, Deep Stacked DAE gives 18% improvements compared to the baseline system.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Denoising x-vectors for Robust Speaker Recognition

Mohammadamini

Matrouf

Noé

2020

The Speaker and Language Recognition Workshop (Odyssey 2020)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In fact, the data in these spaces are almost Gaussian distributed. Previous studies show the effectiveness of denoising techniques in the ivector domain [3,4,5,6,7].…”

Section: Introductionmentioning

confidence: 99%

Data augmentation versus noise compensation for x-vector speaker recognition systems in noisy environments

Amini

Matrouf

2021

2020 28th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

The explosion of available speech data and new speaker modeling methods based on deep neural networks (DNN) have given the ability to develop more robust speaker recognition systems. Among DNN speaker modelling techniques, x-vector system has shown a degree of robustness in noisy environments. Previous studies suggest that by increasing the number of speakers in the training data and using data augmentation more robust speaker recognition systems are achievable in noisy environments. In this work, we want to know if explicit noise compensation techniques continue to be effective despite the general noise robustness of these systems. For this study, we will use two different x-vector networks: the first one is trained on Voxceleb1 (Protocol1), and the second one is trained on Voxceleb1+Voxveleb2 (Protocol2).We propose to add a denoising x-vector subsystem before scoring. Experimental results show that, the x-vector system used in Protocol2 is more robust than the other one used Protocol1. Despite this observation we will show that explicit noise compensation gives almost the same EER relative gain in both protocols. For example, in the Protocol2 we have 21% to 66% improvement of EER with denoising techniques.

show abstract

“…A few recent papers have focused on i-vector mapping, which maps the short utterance i-vector to its long version. In Kheder et al (2016Kheder et al ( , 2018, the authors proposed a probabilistic approach, in which a GMM-based joint model between long and short utterance i-vectors was trained, and a minimum mean square error (MMSE) estimator was applied to transform a short i-vector to its long version. Since the GMM-based mapping function is actually a weighted sum of linear functions, our previous research (Guo et al, 2017b) demonstrates that a proposed non-linear mapping using convolutional neural networks (CNNs) outperforms the GMM-based linear mapping methods across different conditions.…”

Section: Introductionmentioning

confidence: 99%

Deep neural network based i-vector mapping for speaker verification using short utterances

Guo

Qian

et al. 2018

Speech Communication

View full text Add to dashboard Cite

Text-independent speaker recognition using short utterances is a highly challenging task due to the large variation and content mismatch between short utterances. I-vector and probabilistic linear discriminant analysis (PLDA) based systems have become the standard in speaker verification applications, but they are less effective with short utterances. In this paper, we first compare two state-of-the-art universal background model (UBM) training methods for i-vector modeling using full-length and short utterance evaluation tasks. The two methods are Gaussian mixture model (GMM) based (denoted I-vector GMM) and deep neural network (DNN) based (denoted as I-vector DNN) methods. The results indicate that the I-vector DNN system outperforms the I-vector GMM system under various durations (from full length to 5 s). However, the performances of both systems degrade significantly as the duration of the utterances decreases. To address this issue, we propose two novel nonlinear mapping methods which train DNN models to map the i-vectors extracted from short utterances to their corresponding long-utterance i-vectors. The mapped i-vector can restore missing information and reduce the variance of the original short-utterance i-vectors. The proposed methods both model the joint representation of short and long utterance i-vectors: the first method trains an autoencoder first using concatenated short and long utterance i-vectors and then uses the pre-trained weights to initialize a supervised regression model from the short to long version; the second method jointly trains the supervised regression model with an autoencoder reconstructing the short utterance i-vector itself. Experimental results using the NIST SRE 2010 dataset show that both methods provide significant improvement and result in a 24.51% relative improvement in Equal Error Rates (EERs) from a baseline system. In order to learn a better joint representation, we further investigate the effect of a deep encoder with residual blocks, and the results indicate that the residual network can further improve the EERs of a baseline system by up to 26.47%. Moreover, in order to improve the short i-vector mapping to its long version, an additional vector, which represents the average value of phoneme posteriors across frames, is also added to the input, and results in a 28.43% improvement. When further testing the best-validated models of SRE10 on the Speaker In The Wild (SITW) dataset, the methods result in a 23.12% improvement on arbitrary-duration (1-5 s) short-utterance conditions.

show abstract

A Unified Joint Model to Deal With Nuisance Variabilities in the i-Vector Space

Cited by 10 publications

References 35 publications

Denoising x-vectors for Robust Speaker Recognition

Denoising x-vectors for Robust Speaker Recognition

Data augmentation versus noise compensation for x-vector speaker recognition systems in noisy environments

Deep neural network based i-vector mapping for speaker verification using short utterances

Contact Info

Product

Resources

About