Text-dependent Speaker Verification Task Research Articles

A Simple Distortion-Free Method to Handle Variable Length Sequences for Recurrent Neural Networks in Text Dependent Speaker Verification

Recurrent neural networks (RNNs) can model the time-dependency of time-series data. It has also been widely used in text-dependent speaker verification to extract speaker-and-phrase-discriminant embeddings. As with other neural networks, RNNs are trained in mini-batch units. In order to feed input sequences into an RNN in mini-batch units, all the sequences in each mini-batch must have the same length. However, the sequences have variable lengths and we have no knowledge of these lengths in advance. Truncation/padding are most commonly used to make all sequences the same length. However, the truncation/padding causes information distortion because some information is lost and/or unnecessary information is added, which can degrade the performance of text-dependent speaker verification. In this paper, we propose a method to handle variable length sequences for RNNs without adding information distortion by truncating the output sequence so that it has the same length as corresponding original input sequence. The experimental results for the text-dependent speaker verification task in part 2 of RSR 2015 show that our method reduces the relative equal error rate by approximately 1.3% to 27.1%, depending on the task, compared to the baselines but with an associated, small overhead in execution time.

Articulatory movement features for short-duration text-dependent speaker verification

During our pronunciation process, the position and movement properties of articulators such as tongue, jaw, lips, etc are mainly captured by the articulatory movement features (AMFs). This paper investigates to use the AMFs for short-duration text-dependent speaker verification. The AMFs can characterize the relative motion trajectory of articulators of individual speakers directly, which is rarely affected by the external environment. Therefore, we expect that, the AMFs are superior to the traditional acoustic features, such as mel-frequency cepstral coefficients (MFCC), to characterize the speaker identity differences between speakers. The speaker similarity scores measured by the dynamic time warping (DTW) algorithm are used to make the speaker verification decisions. Experimental results show that the AMFs can bring significant performance gains over the traditional MFCC features for short-duration text-dependent speaker verification task.

Text-dependent speaker verification based on i-vectors, Neural Networks and Hidden Markov Models

Inspired by the success of Deep Neural Networks (DNN) in text-independent speaker recognition, we have recently demonstrated that similar ideas can also be applied to the text-dependent speaker verification task. In this paper, we describe new advances with our state-of-the-art i-vector based approach to text-dependent speaker verification, which also makes use of different DNN techniques. In order to collect sufficient statistics for i-vector extraction, different frame alignment models are compared such as GMMs, phonemic HMMs or DNNs trained for senone classification. We also experiment with DNN based bottleneck features and their combinations with standard MFCC features. We experiment with few different DNN configurations and investigate the importance of training DNNs on 16 kHz speech. The results are reported on RSR2015 dataset, where training material is available for all possible enrollment and test phrases. Additionally, we report results also on more challenging RedDots dataset, where the system is built in truly phrase-independent way.

Generalized I-vector Representation with Phonetic Tokenizations and Tandem Features for both Text Independent and Text Dependent Speaker Verification

This paper presents a generalized i-vector representation framework with phonetic tokenization and tandem features for text independent as well as text dependent speaker verification. In the conventional i-vector framework, the tokens for calculating the zero-order and first-order Baum-Welch statistics are Gaussian Mixture Model (GMM) components trained from acoustic level MFCC features. Yet besides MFCC, we believe that phonetic information makes another direction that can benefit the system performance. Our contribution in this paper lies in integrating phonetic information into the i-vector representation by several extensions, forming a more generalized i-vector framework. First, the tokens for calculating the zero-order statistics is extended from the MFCC trained GMM components to phonetic phonemes, trigrams and tandem feature trained GMM components, using phoneme posterior probabilities. Second, given the zero-order statistics (posterior probabilities on tokens), the feature used to calculate the first-order statistics is also extended from MFCC to tandem feature, and is not necessarily the same feature employed by the tokenizer. Third, the zero-order and first-order statistics vectors are then concatenated and represented by the simplified supervised i-vector approach followed by the standard Probabilistic Linear Discriminant Analysis (PLDA) back-end. We study different token and feature combinations, and we show that the feature level fusion of acoustic level MFCC features and phonetic level tandem features with GMM based i-vector representation achieves the best performance for text independent speaker verification. Furthermore, we demonstrate that the phonetic level phoneme constraints introduced by the tandem features help the text dependent speaker verification system to reject wrong password trials and improve the performance dramatically. Experimental results are reported on the NIST SRE 2010 common condition 5 female part task and the RSR 2015 part 1 female part task for text independent and text dependent speaker verification, respectively. For the text independent speaker verification task, the proposed generalized i-vector representation outperforms the i-vector baseline by relatively 53 % in terms of equal error rate (EER) and norm minDCF values. For the text dependent speaker verification task, our proposed approach also reduced the EER significantly from 23 % to 90 % relatively for different types of trials.

Telephone Channel Compensation in Speaker Verification Using a Polynomial Approximation in the Log-Filter-Bank Energy Domain

This correspondence presents a novel feature-space channel compensation technique that models the convolutional distortion in the log-energy mel-filter domain by means of a polynomial approximation. The proposed parametric distortion model generates appropriate constraints in the spectral domain that help to improve the channel cancelling estimation with limited data. In a text-dependent speaker verification task, the polynomial-based channel estimation scheme can lead to reductions in equal error rate (EER) as great as 22% and 8% when compared with the baseline system and with the standard cepstral bias removal approach, respectively, with no significant increase in computational load.

Channel Robust Feature Transformation Based on Filter-Bank Energy Filtering

This correspondence proposes a novel feature transform for channel robustness with short utterances. In contrast to well-known techniques based on feature trajectory filtering, the presented procedure aims to reduce the time-varying component of channel distortion by applying a bandpass filter along the Mel frequency domain on a frame-by-frame basis. By doing so, the channel cancelling effect due to conventional feature trajectory filtering methods is enhanced. The filtering parameters are defined by employing a novel version of relative importance analysis based on a discriminant function. Experiments with telephone speech on a text-dependent speaker verification task show that the proposed scheme can lead to reductions of 8.6% in equal error rate when compared with the baseline system. Also, when applied in combination with cepstral mean normalization and RASTA, the presented technique leads to further reductions of 9.7% and 4.3% in equal error rate, respectively, when compared with those methods isolated.

On-Line Linear Combination of Classifiers Based on Incremental Information in Speaker Verification

A novel multiclassifier system (MCS) strategy is proposed and applied to a text-dependent speaker verification task. The presented scheme optimizes the linear combination of classifiers on an on-line basis. In contrast to ordinary MCS approaches, neither a priori distributions nor pre-tuned parameters are required. The idea is to improve the most accurate classifier by making use of the incremental information provided by the second classifier. The on-line multiclassifier optimization approach is applicable to any pattern recognition problem. The proposed method needs neither a priori distributions nor pre-estimated weights, and does not make use of any consideration about training/testing matching conditions. Results with Yoho database show that the presented approach can lead to reductions in equal error rate as high as 28%, when compared with the most accurate classifier, and 11% against a standard method for the optimization of linear combination of classifiers.

Preliminary experiments in speaker verification using time-dependent largest Lyapunov exponents

The characterization of a speech signal using non-linear dynamical features has been the focus of intense research lately. In this work, the results obtained with time-dependent largest Lyapunov exponents (TDLEs) in a text-dependent speaker verification task are reported. The baseline system used Gaussian mixture models (GMMs), obtained from the adaptation of a universal background model (UBM), for the speaker voice models. Sixteen cepstral and 16 delta cepstral features were used in the experiments, and it is shown how the addition of TDLEs can improve the system’s accuracy. Cepstral mean subtraction was applied to all features in the tests for channel equalization, and silence frames were discarded. The corpus used, obtained from a subset of the Center for Spoken Language Understanding (CSLU) Speaker Recognition corpus, consisted of telephone speech from 91 different speakers.

Robust speaker verification with state duration modeling

This paper addresses the problem of state duration modeling in the Viterbi algorithm in a text-dependent speaker verification task. The results presented in this paper suggest that temporal constraints can lead to reductions of 10% and 20% in the error rates with signals corrupted by noise at SNR equal to 6 and 0 dB, respectively, and that the accurate statistical modeling of state duration (e.g. with gamma probability distribution) does not seem to be very relevant if maximal and minimal state duration restrictions are imposed. In contrast, temporal restrictions do not seem to give any improvement in a speaker verification task with clean speech or high SNR. It is also shown that state duration constraints can easily be applied with the likelihood normalization metrics based on speaker-dependent temporal parameters. Finally, the results here presented show that word position-dependent state duration parameters give no significant improvement when compared with the word position-independent approach if the coarticulation effect between contiguous words is low.