Standard I-vector Research Articles

Emotional Variability Analysis Based I-Vector for Speaker Verification in Under-Stress Conditions

Emotional conditions cause changes in the speech production system. It produces the differences in the acoustical characteristics compared to neutral conditions. The presence of emotion makes the performance of a speaker verification system degrade. In this paper, we propose a speaker modeling that accommodates the presence of emotions on the speech segments by extracting a speaker representation compactly. The speaker model is estimated by following a similar procedure to the i-vector technique, but it considerate the emotional effect as the channel variability component. We named this method as the emotional variability analysis (EVA). EVA represents the emotion subspace separately to the speaker subspace, like the joint factor analysis (JFA) model. The effectiveness of the proposed system is evaluated by comparing it with the standard i-vector system in the speaker verification task of the Speech Under Simulated and Actual Stress (SUSAS) dataset with three different scoring methods. The evaluation focus in terms of the equal error rate (EER). In addition, we also conducted an ablation study for a more comprehensive analysis of the EVA-based i-vector. Based on experiment results, the proposed system outperformed the standard i-vector system and achieved state-of-the-art results in the verification task for the under-stressed speakers.

Adversarially Learned Total Variability Embedding for Speaker Recognition with Random Digit Strings.

Over the recent years, various research has been conducted to investigate methods for verifying users with a short randomized pass-phrase due to the increasing demand for voice-based authentication systems. In this paper, we propose a novel technique for extracting an i-vector-like feature based on an adversarially learned inference (ALI) model which summarizes the variability within the Gaussian mixture model (GMM) distribution through a nonlinear process. Analogous to the previously proposed variational autoencoder (VAE)-based feature extractor, the proposed ALI-based model is trained to generate the GMM supervector according to the maximum likelihood criterion given the Baum–Welch statistics of the input utterance. However, to prevent the potential loss of information caused by the Kullback–Leibler divergence (KL divergence) regularization adopted in the VAE-based model training, the newly proposed ALI-based feature extractor exploits a joint discriminator to ensure that the generated latent variable and the GMM supervector are more realistic. The proposed framework is compared with the conventional i-vector and VAE-based methods using the TIDIGITS dataset. Experimental results show that the proposed method can represent the uncertainty caused by the short duration better than the VAE-based method. Furthermore, the proposed approach has shown great performance when applied in association with the standard i-vector framework.

End-to-end DNN based text-independent speaker recognition for long and short utterances

Recently several end-to-end speaker verification systems based on deep neural networks (DNNs) have been proposed. These systems have been proven to be competitive for text-dependent tasks as well as for text-independent tasks with short utterances. However, for text-independent tasks with longer utterances, end-to-end systems are still outperformed by standard i-vector + PLDA systems. In this work, we present an end-to-end speaker verification system that is initialized to mimic an i-vector + PLDA baseline. The system is then further trained in an end-to-end manner but regularized so that it does not deviate too far from the initial system. In this way we mitigate overfitting which normally limits the performance of end-to-end systems. The proposed system outperforms the i-vector + PLDA baseline on both long and short duration utterances.

Generalizing I-Vector Estimation for Rapid Speaker Recognition

An i-vector is a compact representation that captures both the speaker and session variabilities rendered in a spoken utterance. Over the past years, it has prevailed over other techniques and is now the de facto representation for text-independent speaker recognition. Standard i-vector extraction requires intense computation at run-time. Reducing the computation will allow effective use of i-vector in more applications. Such intense computation arises from the posterior covariance matrix, when estimating the i-vector. There have been studies on how to simplify the computation of posterior covariance matrix with modest success. In this paper, we propose a novel approach to i-vector extraction without the need to evaluate the full posterior covariance thereby speeding up the run-time extraction process. This is achieved by generalizing the i-vector estimation in two ways. First, we introduce the use of occupancy reweighting in conjunction with whitening over the Baum-Welch statistics as part of the preprocessing step. Second, we introduce the so-called subspace-orthogonalizing prior (SOP) to replace the standard Gaussian prior in i-vector formulation. Experiments conducted on the extended-core task of NIST SRE'10 show that the proposed rapid SOP approach achieves considerable speed-up over the standard i-vector with comparable equal error rates.

Curriculum Learning Based Approaches for Noise Robust Speaker Recognition

Performance of speaker identification (SID) systems is known to degrade rapidly in the presence of mismatch such as noise and channel degradations. This study introduces a novel class of curriculum learning (CL) based algorithms for noise robust speaker recognition. We introduce CL-based approaches at two stages within a state-of-the-art speaker verification system: at the i-Vector extractor estimation and at the probabilistic linear discriminant (PLDA) back-end. Our proposed CL-based approaches operate by categorizing the available training data into progressively more challenging subsets using a suitable difficulty criterion. Next, the corresponding training algorithms are initialized with a subset that is closest to a clean noise-free set, and progressively moving to subsets that are more challenging for training as the algorithms progress. We evaluate the performance of our proposed approaches on the noisy and severely degraded data from the DARPA RATS SID task, and show consistent and significant improvement across multiple test sets over a baseline SID framework with a standard i-Vector extractor and multisession PLDA-based back-end. We also construct a very challenging evaluation set by adding noise to the NIST SRE 2010 C5 extended condition trials, where our proposed CL-based PLDA is shown to offer significant improvements over a traditional PLDA based back-end.

Study of Senone-Based Deep Neural Network Approaches for Spoken Language Recognition

This paper compares different approaches for using deep neural networks (DNNs) trained to predict senone posteriors for the task of spoken language recognition (SLR). These approaches have recently been found to outperform various baseline systems on different datasets, but they have not yet been compared to each other or to a common baseline. Two of these approaches use the DNNs to generate feature vectors which are then processed in different ways to predict the score of each language given a test sample. The features are extracted either from a bottleneck layer in the DNN or from the output layer. In the third approach, the standard i-vector extraction procedure is modified to use the senones as classes and the DNN to predict the zeroth order statistics. We compare these three approaches and conclude that the approach based on bottleneck features followed by i-vector modeling outperform the other two approaches. We also show that score-level fusion of some of these approaches leads to gains over using a single approach for short-duration test samples. Finally, we demonstrate that fusing systems that use DNNs trained with several languages leads to improvements in performance over the best single system, and we propose an adaptation procedure for DNNs trained with languages with less available data. Overall, we show improvements between 40% and 70% relative to a state-of-the-art Gaussian mixture model (GMM) i-vector system on test durations from 3 seconds to 120 seconds on two significantly different tasks: the NIST 2009 language recognition evaluation task and the DARPA RATS language identification task.

Quasi-Factorial Prior for i-vector Extraction

We analyze the i-vector extraction from the perspective of the prior distribution exerted on the mean supervector of Gaussian mixture model (GMM). To this end, we start off with the analysis of the subspace prior which leads to the compressed representation in the standard i-vector extraction. We then propose the use of quasi-factorial prior and show how it impacts the total variability space and its application for i-vector extraction. The quasi-factorial prior could be used in a standalone manner, or in combination with a subspace prior. In the latter context, we found that the performance of the standard i-vector can be greatly improved with the use of quasi-factorial prior followed by a subspace prior. This assertion is confirmed through experiments conducted on the NIST 2010 Speaker Recognition Evaluation (SRE10) dataset.

Maximum Likelihood Acoustic Factor Analysis Models for Robust Speaker Verification in Noise

Recent speaker recognition/verification systems generally utilize an utterance dependent fixed dimensional vector as features to Bayesian classifiers. These vectors, known as i-Vectors, are lower dimensional representations of Gaussian Mixture Model (GMM) mean super-vectors adapted from a Universal Background Model (UBM) using speech utterance features, and extracted utilizing a Factor Analysis (FA) framework. This method is based on the assumption that the speaker dependent information resides in a lower dimensional sub-space. In this study, we utilize a mixture of Acoustic Factor Analyzers (AFA) to model the acoustic features instead of a GMM-UBM. Following our previously proposed AFA technique (“Acoustic factor analysis for robust speaker verification,” by Hasan and Hansen, IEEE Trans. Audio, Speech, Lang. Process., vol. 21, no. 4, April 2013), this model is based on the assumption that the speaker relevant information lies in a lower dimensional subspace in the multi-dimensional feature space localized by the mixture components. Unlike our previous method, here we train the AFA-UBM model directly from the data using an Expectation-Maximization (EM) algorithm. This method shows improved robustness to noise as the nuisance dimensions are removed in each EM iteration. Two variants of the AFA model are considered utilizing an isotropic and diagonal covariance residual term. The method is integrated within a standard i-Vector system where the hidden variables of the model, termed as acoustic factors, are utilized as the input for total variability modeling. Experimental results obtained on the 2012 National Institute of Standards and Technology (NIST) Speaker Recognition Evaluation (SRE) core-extended trials indicate the effectiveness of the proposed strategy in both clean and noisy conditions.