Features based on filtering and spectral peaks in autocorrelation domain for robust speech recognition

In this paper, a set of features derived by filtering and spectral peak extraction in autocorrelation domain are proposed. We focus on the effect of the additive noise on speech recognition. Assuming that the channel characteristics and additive noises are stationary, these new features improve the robustness of speech recognition in noisy conditions. In this approach, initially, the autocorrelation sequence of a speech signal frame is computed. Filtering of the autocorrelation of speech signal is carried out in the second step, and then, the short-time power spectrum of speech is obtained from the speech signal through the fast Fourier transform. The power spectrum peaks are then calculated by differentiating the power spectrum with respect to frequency. The magnitudes of these peaks are then projected onto the mel-scale and pass the filter bank. Finally, a set of cepstral coefficients are derived from the outputs of the filter bank. The effectiveness of the new features for speech recognition in noisy conditions will be shown in this paper through a number of speech recognition experiments.A task of multi-speaker isolated-word recognition and another one of multi-speaker continuous speech recognition with various artificially added noises such as factory, babble, car and F16 were used in these experiments. Also, a set of experiments were carried out on Aurora 2 task. Experimental results show significant improvements under noisy conditions in comparison to the results obtained using traditional feature extraction methods. We have also reported the results obtained by applying cepstral mean normalization on the methods to get robust features against both additive noise and channel distortion.     

基于差分过零峰值幅度特征的抗噪语音识别

针对多数语音识别系统在噪音环境下性能急剧下降的问题,提出了一种新的语音识别特征提取方法。该方法是建立在听觉模型的基础上,通过组合语音信号和其差分信号的上升过零率获得频率信息,通过峰值检测和非线性幅度加权来获取强度信息,二者组合在一起,得到输出语音特征,再分别用BP神经网络和HMM进行训练和识别。仿真实现了不同信噪比下不依赖人的50词的语音识别,给出了识别的结果,证明了组合差分信息的过零与峰值幅度特征具有较强的抗噪声性能。     

Robust vocabulary recognition clustering model using an average estimator least mean square filter in noisy environments

Noise estimation and detection algorithms must adapt to a changing environment quickly, so they use a least mean square (LMS) filter. However, there is a downside. An LMS filter is very low, and it consequently lowers speech recognition rates. In order to overcome such a weak point, we propose a method to establish a robust speech recognition clustering model for noisy environments. Since this proposed method allows the cancelation of noise with an average estimator least mean square (AELMS) filter in a noisy environment, a robust speech recognition clustering model can be established. With the AELMS filter, which can preserve source features of speech and decrease the degradation of speech information, noise in a contaminated speech signal gets canceled, and a Gaussian state model is clustered as a method to make noise more robust. By composing a Gaussian clustering model, which is a robust speech recognition clustering model, in a noisy environment, recognition performance was evaluated. The study shows that the signal-to-noise ratio of speech, which was improved by canceling environment noise that kept changing, was enhanced by 2.8 dB on average, and recognition rate improved by 4.1 %.     

基于双微阵列与卷积神经网络的语音识别方法

为解决噪声环境下语音识别率降低以及传统波束形成算法难以处理空间噪声的问题,基于双微阵列结构提出了一种改进的最小方差无畸变响应（MVDR）波束形成方法。首先,采用对角加载提高双微阵列增益,并利用递归矩阵求逆降低计算复杂度;然后,通过后置调制域谱减法对语音作进一步处理,解决了一般谱减法容易产生音乐噪声的问题,有效减小了语音畸变,获得了良好的噪声抑制效果;最后,采用卷积神经网络（CNN）进行语音模型的训练,提取语音深层次的特征,有效地解决了语音信号多样性问题。实验结果表明,提出的方法在经CNN训练的语音识别系统模型中取得了较好的识别效果,在信噪比为10 dB的F16噪声环境下的语音识别率达到了92.3%,具有良好的稳健性。     

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.     

Transforming Binary Uncertainties for Robust Speech Recognition

Recently, several algorithms have been proposed to enhance noisy speech by estimating a binary mask that can be used to select those time-frequency regions of a noisy speech signal that contain more speech energy than noise energy. This binary mask encodes the uncertainty associated with enhanced speech in the linear spectral domain. The use of the cepstral transformation smears the information from the noise dominant time-frequency regions across all the cepstral features. We propose a supervised approach using regression trees to learn the nonlinear transformation of the uncertainty from the linear spectral domain to the cepstral domain. This uncertainty is used by a decoder that exploits the variance associated with the enhanced cepstral features to improve robust speech recognition. Systematic evaluations on a subset of the Aurora4 task using the estimated uncertainty show substantial improvement over the baseline performance across various noise conditions.     

基于对数能量倒谱特征的端点检测算法

端点检测技术是语音识别的关键技术之一,为了克服传统倒谱距离语音端点检测算法在低信噪比下检测效果的不理想,将对数能量（LE）特征和倒谱（C）特征相结合,提出了一种新的对数能量倒谱特征（LEC）,采用模糊C均值聚类和贝叶斯信息准则（BIC）方法估计特征门限,得出了正确的语音端点判断,在三种典型噪声下,对信噪比从－5 dB到15 dB的带噪声语音进行仿真,结果表明LEC法的检测错误率仅为20.25%,明显低于倒谱法和对数能量法,能有效地确定语音的端点并改善语音识别效果。     

SMFCC:一种新的语音信号特征提取方法

针对说话人识别系统中存在的有效语音特征提取以及噪声影响的问题,提出了一种新的语音特征提取方法——基于S变换的美尔倒谱系数(SMFCC)。该方法是在传统美尔倒谱系数(MFCC)的基础上利用S变换的二维时频多分辨率特性,以及奇异值分解(SVD)方法的二维时频矩阵有效去噪性,并结合相关统计分析方法最终获得语音特征。采用TIMIT语音数据库,将所提的特征和现有特征进行对比实验。SMFCC特征的等错误率(EER)和最小检测代价(MinDCF)均小于线性预测倒谱系数(LPCC)、MFCC及其结合方法LMFCC,比MFCC的EER和MinDCF08分别下降了3.6%与17.9%。实验结果表明所提方法能够有效去除语音信号中的噪声,提升局部分辨率。     

Adaptive wavelet shrinkage for noise robust speaker recognition

Speaker recognition faces many practical difficulties, among which signal inconsistency due to environmental and acquisition channel factors is most challenging. The noise imposed to the voice signal varies greatly and a priori noise model is usually unavailable. In this article, we propose a robust speaker recognition method that employs a novel adaptive wavelet shrinkage method for noise suppression. In our method, wavelet subband coefficient thresholds are automatically computed, which are proportional to the noise contamination. In the application of wavelet shrinkage for noise removal, a dual-threshold strategy is developed to suppress noise, preserve signal coefficients and minimize the introduction of artifacts. The recognition is achieved using modification of Mel-frequency cepstral coefficient of overlapped voice signal segments. The efficacy of our method is evaluated with voice signals from two public available speech signal databases and is compared with state-of-the-art methods. It is demonstrated that our proposed method exhibits great robustness in various noise conditions. The improvement is significant especially when noise dominates the underlying speech.     

Auditory driven subband speech enhancement for automatic recognition of noisy speech

Speech recognizers achieve high recognition accuracy under quiet acoustic environments, but their performance degrades drastically when they are deployed in real environments, where the speech is degraded by additive ambient noise. This paper advocates a two phase approach for robust speech recognition in such environment. Firstly, a front end subband speech enhancement with adaptive noise estimation (ANE) approach is used to filter the noisy speech. The whole noisy speech spectrum is portioned into eighteen dissimilar subbands based on Bark scale and noise power from each subband is estimated by the ANE approach, which does not require the speech pause detection. Secondly, the filtered speech spectrum is processed by the non parametric frequency domain algorithm based on human perception along with the back end building a robust classifier to recognize the utterance. A suite of experiments is conducted to evaluate the performance of the speech recognizer in a variety of real environments, with and without the use of a front end speech enhancement stage. Recognition accuracy is evaluated at the word level, and at a wide range of signal to noise ratios for real world noises. Experimental evaluations show that the proposed algorithm attains good recognition performance when signal to noise ratio is lower than 5 dB.     

语音情感智能识别的建模与仿真

语音情感信息具有非线性、信息冗余、高维等复杂特点,数据含有大量噪声,传统识别模型难以消除冗余和噪声信息,导致语音情感识别正确率十分低.为了提高语音情感识别正确率,利用小波分析去噪和神经网络的非线性处理能力,提出一种基于过程神经元网络的语音情感智能识别模型.采用小波分析对语音情感信号进行去噪处理,利用主成分分析消除语音情感特征中的冗余信息,采用过程神经元网络对语音情感进行分类识别.仿真结果表明,基于过程神经元网络的识别模型的识别率比K近邻提高了13％,比支持向量机提高了8.75％,该模型是一种有效的语音情感智能识别工具.     

Sinusoidal model-based analysis and classification of stressed speech

In this paper, a sinusoidal model has been proposed for characterization and classification of different stress classes (emotions) in a speech signal. Frequency, amplitude and phase features of the sinusoidal model are analyzed and used as input features to a stressed speech recognition system. The performances of sinusoidal model features are evaluated for recognition of different stress classes with a vector-quantization classifier and a hidden Markov model classifier. To find the effectiveness of these features for recognition of different emotions in different languages, speech signals are recorded and tested in two languages, Telugu (an Indian language) and English. Average stressed speech index values are proposed for comparing differences between stress classes in a speech signal. Results show that sinusoidal model features are successful in characterizing different stress classes in a speech signal. Sinusoidal features perform better compared to the linear prediction and cepstral features in recognizing the emotions in a speech signal.     

Characterization and recognition of emotions from speech using excitation source information

This paper explores the excitation source features of speech production mechanism for characterizing and recognizing the emotions from speech signal. The excitation source signal is obtained from speech signal using linear prediction (LP) analysis, and it is also known as LP residual. Glottal volume velocity (GVV) signal is also used to represent excitation source, and it is derived from LP residual signal. Speech signal has high signal to noise ratio around the instants of glottal closure (GC). These instants of glottal closure are also known as epochs. In this paper, the following excitation source features are proposed for characterizing and recognizing the emotions: sequence of LP residual samples and their phase information, parameters of epochs and their dynamics at syllable and utterance levels, samples of GVV signal and its parameters. Auto-associative neural networks (AANN) and support vector machines (SVM) are used for developing the emotion recognition models. Telugu and Berlin emotion speech corpora are used to evaluate the developed models. Anger, disgust, fear, happy, neutral and sadness are the six emotions considered in this study. About 42 % to 63 % of average emotion recognition performance is observed using different excitation source features. Further, the combination of excitation source and spectral features has shown to improve the emotion recognition performance up to 84 %.     

Audio-visual speech modeling for continuous speech recognition

This paper describes a speech recognition system that uses both acoustic and visual speech information to improve recognition performance in noisy environments. The system consists of three components: a visual module; an acoustic module; and a sensor fusion module. The visual module locates and tracks the lip movements of a given speaker and extracts relevant speech features. This task is performed with an appearance-based lip model that is learned from example images. Visual speech features are represented by contour information of the lips and grey-level information of the mouth area. The acoustic module extracts noise-robust features from the audio signal. Finally the sensor fusion module is responsible for the joint temporal modeling of the acoustic and visual feature streams and is realized using multistream hidden Markov models (HMMs). The multistream method allows the definition of different temporal topologies and levels of stream integration and hence enables the modeling of temporal dependencies more accurately than traditional approaches. We present two different methods to learn the asynchrony between the two modalities and how to incorporate them in the multistream models. The superior performance for the proposed system is demonstrated on a large multispeaker database of continuously spoken digits. On a recognition task at 15 dB acoustic signal-to-noise ratio (SNR), acoustic perceptual linear prediction (PLP) features lead to 56% error rate, noise robust RASTA-PLP (relative spectra) acoustic features to 7.2% error rate and combined noise robust acoustic features and visual features to 2.5% error rate     

Speech enhancement based on stationary bionic wavelet transform and maximum a posterior estimator of magnitude-squared spectrum

Numerous efforts have focused on the problem of reducing the impact of noise on the performance of various speech systems such as speech coding, speech recognition and speaker recognition. These approaches consider alternative speech features, improved speech modeling, or alternative training for acoustic speech models. In this paper, we propose a new speech enhancement technique, which integrates a new proposed wavelet transform which we call stationary bionic wavelet transform (SBWT) and the maximum a posterior estimator of magnitude-squared spectrum (MSS-MAP). The SBWT is introduced in order to solve the problem of the perfect reconstruction associated with the bionic wavelet transform. The MSS-MAP estimation was used for estimation of speech in the SBWT domain. The experiments were conducted for various noise types and different speech signals. The results of the proposed technique were compared with those of other popular methods such as Wiener filtering and MSS-MAP estimation in frequency domain. To test the performance of the proposed speech enhancement system, four objective quality measurement tests [signal to noise ratio (SNR), segmental SNR, Itakura–Saito distance and perceptual evaluation of speech quality] were conducted for various noise types and SNRs. Experimental results and objective quality measurement test results proved the performance of the proposed speech enhancement technique. It provided sufficient noise reduction and good intelligibility and perceptual quality, without causing considerable signal distortion and musical background noise.     

Robust emotional speech classification in the presence of babble noise

Emotional speech recognition (ESR) is a new field of research in the realm of human-computer interactions. Most of the studies in this field are performed in clean environments. Nevertheless, in the real world conditions, there are different noise and disturbance parameters such as car noise, background music, buzz and etc., which can decrease the performance of such recognizing systems. One of the most common noises which can be heard in different places is the babble noise. Because of the similarity of this kind of noise to the desired speech sounds, babble or cross-talk, is highly challenging for different speech-related systems. In this paper, in order to find the most appropriate features for ESR in the presence of babble noise with different signal to noise ratios, 286 features are extracted from speech utterances of two emotional speech datasets in German and Persian. Then the best features are selected among them using different filter and wrapper methods. Finally, different classifiers like Bayes, KNN, GMM, ANN and SVM are used for the selected features in two ways, namely multi-class and binary classifications.     

基于语音增强失真补偿的抗噪声语音识别技术

本文提出了一种基于语音增强失真补偿的抗噪声语音识别算法。在前端,语音增强有效地抑制背景噪声;语音增强带来的频谱失真和剩余噪声是对语音识别不利的因素,其影响将通过识别阶段的并行模型合并或特征提取阶段的倒谱均值归一化得到补偿。实验结果表明,此算法能够在非常宽的信噪比范围内显著的提高语音识别系统在噪声环境下的识别精度,在低信噪比情况下的效果尤其明显,如对-5dB的白噪声,相对于基线识别器,该算法可使误识率下降67.4%。     

基于自适应噪声估计的语音增强技术

针对语音系统受外界强噪声干扰而导致识别精度降低以及通信质量受损的问题,提出一种基于自适应噪声估计的语音增强方法。通过端点检测将语音信号分为语音段与非语音段,对这两种情况的噪声幅度谱分别进行自适应估计,并对谱减法中不具有通用性的假设进行研究从而改进原理公式。实验结果表明,相对于传统谱减法,该方法能更好地抑制音乐噪声,并保持较高清晰度和可懂度,提高了强噪声环境下的语音识别精度和通信质量。     

Phoneme recognition using zerocrossing interval distribution of speech patterns and ANN

The speech signal is modeled using zerocrossing interval distribution of the signal in time domain. The distributions of these parameters are studied over five Malayalam (one of the most popular Indian language) vowels. We found that the distribution patterns are almost similar for repeated utterances of the same vowel and varies from vowel to vowel. These distribution patterns are used for recognizing the vowels using multilayer feed forward artificial neural network. After analyzing the distribution patterns and the vowel recognition results, we realize that the zerocrossing interval distribution parameters can be effectively used for the speech phone classification and recognition. The noise adaptness of this parameter is also studied by adding additive white Gaussian noise at different signal to noise ratio. The computational complexity of the proposed technique is also less compared to the conventional spectral techniques, which includes FFT and Cepstral methods, used in the parameterization of speech signal.