Text-Independent Speaker Verification for Real Fast-Varying Noisy Environments

Investigating Speaker Verification in real-world noisy environments, a novel feature extraction process suitable for suppression of time-varying noise is compared with a fine-tuned spectral subtraction method. The proposed feature extraction process is based on approximating the clean speech and the noise spectral magnitude with a mixture of Gaussian probability density functions (pdfs) by using the Expectation-Maximization algorithm (EM). Subsequently, the Bayesian inference framework is applied to the degraded spectral coefficients, and by employing Minimum Mean Square Error Estimation (MMSE), a closed form solution for the spectral magnitude estimation task is derived. The estimated spectral magnitude finally is incorporated into the Mel-Frequency Cepstral Coefficients (MFCCs) front-end of a baseline text-independent speaker verification system, based on Probabilistic Neural Networks, which participated successfully in the 2002 NIST (National Institute of Standards and Technology of USA) Speaker Recognition Evaluation. A comparative study of the proposed technique for real-world noise types demonstrates a significant performance gain compared to the baseline speech features and to the spectral subtraction enhancement method. Improvements of the absolute speaker verification performance with more than 27% for 0 dB signal-to-noise ratio (SNR), compared to the MFCCs, and with more than 13% for –5 dB SNR, compared to the spectral subtraction version, were obtained in the case of a passing-by aircraft scenario.     

Speaker verification in sensor and acoustic environment mismatch conditions

Our initial speaker verification study exploring the impact of mismatch in training and test conditions finds that the mismatch in sensor and acoustic environment results in significant performance degradation compared to other mismatches like language and style (Haris et al. in Int. J. Speech Technol., 2012). In this work we present a method to suppress the mismatch between the training and test speech, specifically due to sensor and acoustic environment. The method is based on identifying and emphasizing more speaker specific and less mismatch affected vowel-like regions (VLRs) compared to the other speech regions. VLRs are separated from the speech regions (regions detected using voice activity detection (VAD)) using VLR onset point (VLROP) and are processed independently during training and testing of the speaker verification system. Finally, the scores are combined with more weight to that generated by VLRs as those are relatively more speaker specific and less mismatch affected. Speaker verification studies are conducted using the mel-frequency cepstral coefficients (MFCCs) as feature vectors. The speaker modeling is done using the Gaussian mixture model-universal background model and the state-of-the-art i-vector based approach. The experimental results show that for both the systems, proposed approach provides consistent performance improvement on the conversational approach with and without different channel compensation techniques. For instance, with IITG-MV Phase-II dataset for headphone trained and voice recorder test speech, the proposed approach provides a relative improvement of 25.08?% (in EER) for the i-vector based speaker verification systems with LDA and WCCN compared to conventional approach.     

语音识别中基于i-vector的说话人归一化研究

i-vector是反映说话人声学差异的一种重要特征,在目前的说话人识别和说话人验证中显示了有效性。将i-vector应用于语音识别中的说话人的声学特征归一化,对训练数据提取i-vector并利用LBG算法进行无监督聚类．然后对各类分别训练最大似然线性变换并使用说话人自适应训练来实现说话人的归一化。将变换后的特征用于训练和识别．实验表明该方法能够提高语音识别的性能。     

Environment adaptation for robust speaker verification by cascading maximum likelihood linear regression and reinforced learning

In speaker verification over public telephone networks, utterances can be obtained from different types of handsets. Different handsets may introduce different degrees of distortion to the speech signals. This paper attempts to combine a handset selector with (1) handset-specific transformations, (2) reinforced learning, and (3) stochastic feature transformation to reduce the effect caused by the acoustic distortion. Specifically, during training, the clean speaker models and background models are firstly transformed by MLLR-based handset-specific transformations using a small amount of distorted speech data. Then reinforced learning is applied to adapt the transformed models to handset-dependent speaker models and handset-dependent background models using stochastically transformed speaker patterns. During a verification session, a GMM-based handset classifier is used to identify the most likely handset used by the claimant; then the corresponding handset-dependent speaker and background model pairs are used for verification. Experimental results based on 150 speakers of the HTIMIT corpus show that environment adaptation based on the combination of MLLR, reinforced learning and feature transformation outperforms CMS, Hnorm, Tnorm, and speaker model synthesis.     

Adaptation of children’s speech with limited data based on formant-like peak alignment

Automatic recognition of children’s speech using acoustic models trained by adults results in poor performance due to differences in speech acoustics. These acoustical differences are a consequence of children having shorter vocal tracts and smaller vocal cords than adults. Hence, speaker adaptation needs to be performed. However, in real-world applications, the amount of adaptation data available may be less than what is needed by common speaker adaptation techniques to yield reasonable performance. In this paper, we first study, in the discrete frequency domain, the relationship between frequency warping in the front-end and corresponding transformations in the back-end. Three common feature extraction schemes are investigated and their transformation linearity in the back-end are discussed. In particular, we show that under certain approximations, frequency warping of MFCC features with Mel-warped triangular filter banks equals a linear transformation in the cepstral space. Based on that linear transformation, a formant-like peak alignment algorithm is proposed to adapt adult acoustic models to children’s speech. The peaks are estimated by Gaussian mixtures using the Expectation-Maximization (EM) algorithm [Zolfaghari, P., Robinson, T., 1996. Formant analysis using mixtures of Gaussians, Proceedings of International Conference on Spoken Language Processing, 1229–1232]. For limited adaptation data, the algorithm outperforms traditional vocal tract length normalization (VTLN) and maximum likelihood linear regression (MLLR) techniques.     

基于非参数直方图模型的鲁棒说话人识别算法

建立一种非参数模型来刻画说话人的特征分布,并采用地面移动距离来度量分布之间的相似性.该方法能有效地利用有限的数据表达说话人的身份信息,直接计算特征分布与测试语音分布之间的距离,与传统的矢量量化和高斯混合模型相比,不需要通过对所有语音帧计算总平均失真误差和最小相似度,计算简单,主要能够降低系统对数据量的依赖性.并且通过自适应直方图均衡化方法对原始语音特征进行修正,使得噪声环境下获得的语音特征经过修正后更符合真实分布,增强了特征的抗噪性.实验表明,本文提出的方法在噪声环境下的短语音说话人识别系统中表现出较强的优势.     

Efficient Noise Robust Feature Extraction Algorithms for Distributed Speech Recognition (DSR) Systems

The evolution of robust speech recognition systems that maintain a high level of recognition accuracy in difficult and dynamically-varying acoustical environments is becoming increasingly important as speech recognition technology becomes a more integral part of mobile applications. In distributed speech recognition (DSR) architecture the recogniser's front-end is located in the terminal and is connected over a data network to a remote back-end recognition server. The terminal performs the feature parameter extraction, or the front-end of the speech recognition system. These features are transmitted over a data channel to the remote back-end recogniser. DSR provides particular benefits for the applications of mobile devices such as improved recognition performance compared to using the voice channel and ubiquitous access from different networks with a guaranteed level of recognition performance. A feature extraction algorithm integrated into the DSR system is required to operate in real-time as well as with the lowest possible computational costs.In this paper, two innovative front-end processing techniques for noise robust speech recognition are presented and compared, time-domain based frame-attenuation (TD-FrAtt) and frequency-domain based frame-attenuation (FD-FrAtt). These techniques include different forms of frame-attenuation, improvement of spectral subtraction based on minimum statistics, as well as a mel-cepstrum feature extraction procedure. Tests are performed using the Slovenian SpeechDat II fixed telephone database and the Aurora 2 database together with the HTK speech recognition toolkit. The results obtained are especially encouraging for mobile DSR systems with limited sizes of available memory and processing power.     

Text-independent speaker recognition based on the Hurst parameter and the multidimensional fractional Brownian motion model

In this paper, a text-independent automatic speaker recognition (ASkR) system is proposed-the SR/sub Hurst/-which employs a new speech feature and a new classifier. The statistical feature pH is a vector of Hurst (H) parameters obtained by applying a wavelet-based multidimensional estimator (M/spl I.bar/dim/spl I.bar/wavelets ) to the windowed short-time segments of speech. The proposed classifier for the speaker identification and verification tasks is based on the multidimensional fBm (fractional Brownian motion) model, denoted by M/spl I.bar/dim/spl I.bar/fBm. For a given sequence of input speech features, the speaker model is obtained from the sequence of vectors of H parameters, means, and variances of these features. The performance of the SR/sub Hurst/ was compared to those achieved with the Gaussian mixture models (GMMs), autoregressive vector (AR), and Bhattacharyya distance (dB) classifiers. The speech database-recorded from fixed and cellular phone channels-was uttered by 75 different speakers. The results have shown the superior performance of the M/spl I.bar/dim/spl I.bar/fBm classifier and that the pH feature aggregates new information on the speaker identity. In addition, the proposed classifier employs a much simpler modeling structure as compared to the GMM.     

Speaker adaptation in a large-vocabulary Gaussian HMM recognizer

The problem of using a small amount of speech data to adapt a set of Gaussian HMMs (hidden Markov models) that have been trained on one speaker to recognize the speech of another is considered. The authors experimented with a phoneme-dependent spectral mapping for adapting the mean vectors of the multivariate Gaussian distributions (a method analogous to the confusion matrix method that has been used to adapt discrete HMMs), and a heuristic for estimating covariance matrices from small amounts of data. The best results were obtained by training the mean vectors individually from the adaptation data and using the heuristic to estimate distinct covariance matrices for each phoneme     

文本无关说话人识别中句级特征提取方法研究综述EI北大核心CSCD

句级(Utterance-level)特征提取是文本无关说话人识别领域中的重要研究方向之一.与只能刻画短时语音特性的帧级(Frame-level)特征相比,句级特征中包含了更丰富的说话人个性信息;且不同时长语音的句级特征均具有固定维度,更便于与大多数常用的模式识别方法相结合.近年来,句级特征提取的研究取得了很大的进展,鉴于其在说话人识别中的重要地位,本文对近期具有代表性的句级特征提取方法与技术进行整理与综述,并分别从前端处理、基于任务分段式与驱动式策略的特征提取方法,以及后端处理等方面进行论述,最后对未来的研究趋势展开探讨与分析.     

Speaker recognition under stressed condition

This paper presents the feature analysis and design of compensators for speaker recognition under stressed speech conditions. Any condition that causes a speaker to vary his or her speech production from normal or neutral condition is called stressed speech condition. Stressed speech is induced by emotion, high workload, sleep deprivation, frustration and environmental noise. In stressed condition, the characteristics of speech signal are different from that of normal or neutral condition. Due to changes in speech signal characteristics, performance of the speaker recognition system may degrade under stressed speech conditions. Firstly, six speech features (mel-frequency cepstral coefficients (MFCC), linear prediction (LP) coefficients, linear prediction cepstral coefficients (LPCC), reflection coefficients (RC), arc-sin reflection coefficients (ARC) and log-area ratios (LAR)), which are widely used for speaker recognition, are analyzed for evaluation of their characteristics under stressed condition. Secondly, Vector Quantization (VQ) classifier and Gaussian Mixture Model (GMM) are used to evaluate speaker recognition results with different speech features. This analysis help select the best feature set for speaker recognition under stressed condition. Finally, four VQ based novel compensation techniques are proposed and evaluated for improvement of speaker recognition under stressed condition. The compensation techniques are speaker and stressed information based compensation (SSIC), compensation by removal of stressed vectors (CRSV), cepstral mean normalization (CMN) and combination of MFCC and sinusoidal amplitude (CMSA) features. Speech data from SUSAS database corresponding to four different stressed conditions, Angry, Lombard, Question and Neutral, are used for analysis of speaker recognition under stressed condition.     

Speaker recognition using pyramid match kernel based support vector machines

Gaussian mixture model (GMM) based approaches have been commonly used for speaker recognition tasks. Methods for estimation of parameters of GMMs include the expectation-maximization method which is a non-discriminative learning based method. Discriminative classifier based approaches to speaker recognition include support vector machine (SVM) based classifiers using dynamic kernels such as generalized linear discriminant sequence kernel, probabilistic sequence kernel, GMM supervector kernel, GMM-UBM mean interval kernel (GUMI) and intermediate matching kernel. Recently, the pyramid match kernel (PMK) using grids in the feature space as histogram bins and vocabulary-guided PMK (VGPMK) using clusters in the feature space as histogram bins have been proposed for recognition of objects in an image represented as a set of local feature vectors. In PMK, a set of feature vectors is mapped onto a multi-resolution histogram pyramid. The kernel is computed between a pair of examples by comparing the pyramids using a weighted histogram intersection function at each level of pyramid. We propose to use the PMK-based SVM classifier for speaker identification and verification from the speech signal of an utterance represented as a set of local feature vectors. The main issue in building the PMK-based SVM classifier is construction of a pyramid of histograms. We first propose to form hard clusters, using k-means clustering method, with increasing number of clusters at different levels of pyramid to design the codebook-based PMK (CBPMK). Then we propose the GMM-based PMK (GMMPMK) that uses soft clustering. We compare the performance of the GMM-based approaches, and the PMK and other dynamic kernel SVM-based approaches to speaker identification and verification. The 2002 and 2003 NIST speaker recognition corpora are used in evaluation of different approaches to speaker identification and verification. Results of our studies show that the dynamic kernel SVM-based approaches give a significantly better performance than the state-of-the-art GMM-based approaches. For speaker recognition task, the GMMPMK-based SVM gives a performance that is better than that of SVMs using many other dynamic kernels and comparable to that of SVMs using state-of-the-art dynamic kernel, GUMI kernel. The storage requirements of the GMMPMK-based SVMs are less than that of SVMs using any other dynamic kernel.     

一种基于语音组成单位的说话人识别算法

以线性预测系数为特征通过高斯混合模型的迭代算法对训练样本的初始k均值聚类结果进行优化,得到语音组成单位的表示.以语音组成单位的模式匹配为基础,提出一种文本无关说话人确认的方法——均值法,以及一种文本无关说话人辨认方法.实验结果表明,即使在短时语音下本文方法都能取得较好效果.     

基于独立分量分析和矢量量化的说话人识别

使用独立分量分析（ICA）来提取说话人特征并与矢量量化（VQ）判决方法相结合,实现了一个高性能的基于ICA特征的VQ （ICA VQ）说话人识别系统。通过ICA变换得到说话人语音特征基函数系数用于生成VQ码书,并导出包含能量失真的ICA VQ码书失真测度和质心确定条件,生成最终的判决。仿真实验中ICA提取的特征分别用于不同系统实现说话人确认任务,各系统的DET曲线对比验证了VQ方法用于ICA特征分类判决的优势,同时不同码书尺寸下的等差率（EER）对比证明了VQ码书设计的有效性。     

改进的多窗谱MFCC在说话人确认中的应用

语音中存在加性噪声降低了MFCC参数的鲁棒性,使得说话人确认系统性能下降。多窗谱MFCC引入了多窗谱估计技术在增强 MFCC 特征的噪声鲁棒性上取得了一定效果,但改善的程度有限。为了使 MFCC 参数对噪声具有更强的鲁棒性,提出了一种改进的多窗谱 MFCC 提取算法。改进算法在多窗谱 MFCC 的基础上引入谱减思想,谱减法（Spectral Subtraction, SS）能够增强语音并降低噪音的干扰。因此,采用了Multitaper＋SS组合的改进算法融合了两者的优势,具备了更好的性能。仿真结果表明,当测试语音中含有加性噪声时,与多窗谱 MFCC提取算法相比,采用改进的多窗谱 MFCC 的说话人确认系统性能在等错误率 EER 和最小检测代价函数值minDCF两项评测指标上都取得了更好的结果。     

LPC及F0参数组合基于GMM电话语音说话人识别

该文报告了组合LPC参数以及基频F₀的高斯混合模型(GMM)电话语音说话人自动识别技术的实验研究结果。该研究在基线试验中GMM使用16混合共分散对角矩阵,特征量为LPC倒谱系数。而在开发系统测试中分别利用语音的全发话区间和有声区间两部分参数增加基频参数进行试验,并给出实验比较结果。在50人电话通话开放集自动切分语音流实验中正确识别率为76.97%,而提案方法为80.29%,改善率为3.32%。接近人工切分语音流时的识别率82.34%。     

基于KL散度的支持向量机方法及应用研究

针对ICA提取的说话人语音特征,导出以库尔贝克—莱布勒（KL）散度作为距离测度的KL核函数用来设计支持向量机,实现了一个高分辨率的ICA/SVM说话人确认系统.说话人确认的仿真实验结果表明,使用ICA特征基函数系数比直接使用语音数据训练SVM得到的分类间隔大,支持向量少,而且使用KL核函数的ICA/SVM系统确认的等差率也低于其它传统SVM方法,证明了基于KL散度的支持向量机方法在实现分类和判决上具有高效性能.     

A Mixture of Recurrent Neural Networks for Speaker Normalisation

In spite of recent advances in automatic speech recognition, the performance of state-of-the-art speech recognisers fluctuates depending on the speaker. Speaker normalisation aims at the reduction of differences between the acoustic space of a new speaker and the training acoustic space of a given speech recogniser, improving performance. Normalisation is based on an acoustic feature transformation, to be estimated from a small amount of speech signal. This paper introduces a mixture of recurrent neural networks as an effective regression technique to approach the problem. A suitable Vit-erbi-based time alignment procedure is proposed for generating the adaptation set. The mixture is compared with linear regression and single-model connectionist approaches. Speaker-dependent and speaker-independent continuous speech recognition experiments with a large vocabulary, using Hidden Markov Models, are presented. Results show that the mixture improves recognition performance, yielding a 21% relative reduction of the word error rate, i.e. comparable with that obtained with model-adaptation approaches.     

基于分布特征统计的说话人识别

给出了基于公共码书的说话人分布特征的定义。提出了基于分布特征统计的说话人识别算法,根据所有参考说话人的训练语音建立公共码书,实现对语音特征空间的分类,统计各参考说话人训练语音的在公共码字上的分布特征进行建模。识别中引入双序列比对方法进行识别语音的分布特征统计与参考说话人模型间的相似度匹配,实现对说话人的辨认。实验表明,该方法保证识别率的情况下,进一步提高了基于VQ的说话人识别的速度。     

Development and evaluation of online text-independent speaker verification system for remote person authentication

In this paper an online text-independent speaker verification system developed at IIT Guwahati under multivariability condition for remote person authentication is described. The system is developed on a voice server accessible via telephone network using an interactive voice response (IVR) system in which both enrollment and testing can be done online. The speaker verification system is developed using Mel-Frequency Cepstral Coefficients (MFCC) for feature extraction and Gaussian Mixture Model—Universal Background Model (GMM-UBM) for modeling. The performance of the system under multi-variable condition is evaluated using online enrollments and testing from the subjects. The evaluation of the system helps in understanding the impact of several well known issues related to speaker verification such as the effect of environment noise, duration of test speech, robustness of the system against playing recorded speech etc. in an online system scenario. These issues need to be taken care for the development and deployment of speaker verification system in real life applications.