Hierarchical Singleton-Type Recurrent Neural Fuzzy Networks for Noisy Speech Recognition

This paper proposes noisy speech recognition using hierarchical singleton-type recurrent neural fuzzy networks (HSRNFNs). The proposed HSRNFN is a hierarchical connection of two singleton-type recurrent neural fuzzy networks (SRNFNs), where one is used for noise filtering and the other for recognition. The SRNFN is constructed by recurrent fuzzy if-then rules with fuzzy singletons in the consequences, and their recurrent properties make them suitable for processing speech patterns with temporal characteristics. In n words recognition, n SRNFNs are created for modeling n words, where each SRNFN receives the current frame feature and predicts the next one of its modeling word. The prediction error of each SRNFN is used as recognition criterion. In filtering, one SRNFN is created, and each SRNFN recognizer is connected to the same SRNFN filter, which filters noisy speech patterns in the feature domain before feeding them to the SRNFN recognizer. Experiments with Mandarin word recognition under different types of noise are performed. Other recognizers, including multilayer perceptron (MLP), time-delay neural networks (TDNNs), and hidden Markov models (HMMs), are also tested and compared. These experiments and comparisons demonstrate good results with HSRNFN for noisy speech recognition tasks     

Recurrent type-2 fuzzy neural network using Haar wavelet energy and entropy features for speech detection in noisy environments

This paper proposes a new method to detect the boundary of speech in noisy environments. This detection method uses Haar wavelet energy and entropy (HWEE) as detection features. The Haar wavelet energy (HWE) is derived by using the robust band that shows the most significant difference between speech and nonspeech segments at different noise levels. Similarly, the wavelet energy entropy (WEE) is computed by selecting the two wavelet energy bands whose entropy shows the most significant speech/nonspeech difference. The HWEE features are fed as inputs to a recurrent self-evolving interval type-2 fuzzy neural network (RSEIT2FNN) for classification. The RSEIT2FNN is used because it uses type-2 fuzzy sets, which are more robust to noise than type-1 fuzzy sets. The recurrent structure in the RSEIT2FNN helps to remember the context information of a test frame. The RSEIT2FNN outputs are compared with a parameter threshold to determine whether it is a speech or nonspeech period. The HWEE-based RSEIT2FNN detection was applied to speech detection in different noisy environments with different noise levels. Comparisons with different detection methods verified the advantage of the proposed method of using HWEE.     

一种基于模糊神经网络的语音端点检测方法

为了提高语音端点检测的适应性和鲁棒性,提出一种基于小波分析和模糊神经网络的语音端点检测方法。利用小波变换得到语音信号的特征量,以这些特征量为模糊神经网络的输入进行运算,判断出该信号的类别。介绍了信号特征量的提取以及模糊神经网络的模型、学习算法等。实验表明,与传统的检测方法相比,所提出的方法有较好的适应性和鲁棒性,对不同信噪比的信号都有较好的检测能力。     

基于小波神经网络的语音端点检测算法

为了提高语音端点检测效果,将小波分析和神经网络相融合,提出一种基于小波神经网络的语音端点检测算法（WA-PCA-RBF）。利用小波分析提取语音信号的特征向量,采用主成分分析法选择语音信号特征,消除冗余特征,将选择特征向量作为RBF神经网络输入,通过遗传算法优化RBF神经网络参数建立语音端检测模型。结果表明,相对于传统语音端点检测算法,WA-PCA-RBF提高了语音端点检测正确率,具有更好的适应性和鲁棒性,可满足实际系统需求。     

改进动量粒子群优化神经网络的语音端点检测

为了提高语音端点检测率,提出一种改进动量粒子群优化神经网络的语音端点检测算法(WA-IMPSO-BP)。利用小波分析提取语音信号的特征量,将特征向量作为BP神经网络输入进行学习,并采用粒子群算法优化BP神经网络参数,建立语音端检测模型,在Matlab环境下进行仿真实验。仿真结果表明,WA-IMPSO-BP提高了语音端点检测率,有效降低了虚检率和漏检率,表示WA-IMPSO-BP是一种检测率高,抗噪性能强的语音检测算法。     

一种语音端点检测算法及其在DSP上的实现

提出一种基于模糊RBF神经网络的语音端点检测算法。该算法先利用小波分析提取语音信号的特征量,然后将其输入到模糊RBF神经网络进行端点检测运算,并采用以TMS320VC5416DSP为核心的电路进行算法实现。实验结果表明,该系统的端点检测正确率很高,即使在低信噪比时也能正确地判断语音信号的端点。     

车载环境下的语音端点检测

为了提高车载噪声环境下语音端点检测的准确性,提出了一个基于GRU RNN的神经网络结构, 对带噪语音的Log Mel特征序列进行处理,实现语音与噪声的分离,从而恢复出纯净语音的Log Mel特征序列;在此基础上,提出一种新的特征Log Mel Sum,并用该特征进行端点检测。实验结果表明,在车载环境下,本文方法具有很好的端点检测性能。     

Nonlinear enhancement of noisy speech, using continuous attractor dynamics formed in recurrent neural networks

Here, formation of continuous attractor dynamics in a nonlinear recurrent neural network is used to achieve a nonlinear speech denoising method, in order to implement robust phoneme recognition and information retrieval. Formation of attractor dynamics in recurrent neural network is first carried out by training the clean speech subspace as the continuous attractor. Then, it is used to recognize noisy speech with both stationary and nonstationary noise. In this work, the efficiency of a nonlinear feedforward network is compared to the same one with a recurrent connection in its hidden layer. The structure and training of this recurrent connection, is designed in such a way that the network learns to denoise the signal step by step, using properties of attractors it has formed, along with phone recognition. Using these connections, the recognition accuracy is improved 21% for the stationary signal and 14% for the nonstationary one with 0db SNR, in respect to a reference model which is a feedforward neural network.     

非线性系统的鲁棒故障检测与诊断

研究了一类具有未建模动态或扰动的非线性系统的鲁棒故障检测与诊断问题,利用神 经网络、模糊系统或小波网络等对非线性故障模式进行在线逼近的方法进行故障诊断.第一步， 对用于鲁棒故障检测的观测器,建立了保证观测器稳定的增益阵的选择条件;第二步,若检测出 发生故障,则用神经网络、模糊系统或小波网络进行故障的在线估计,建立了估计误差界,结果 显示输出估计误差将收敛到由扰动上界或建模误差上界线性确定的范围内.     

Single-channel speech enhancement in variable noise-level environment

Discusses the problem of single-channel speech enhancement in variable noise-level environment. Commonly used, single-channel subtractive-type speech enhancement algorithms always assume that the background noise level is fixed or slowly varying. In fact, the background noise level may vary quickly. This condition usually results in wrong speech/noise detection and wrong speech enhancement process. In order to solve this problem, we propose a subtractive-type speech enhancement scheme. This new enhancement scheme uses the RTF (refined time-frequency parameter)-based RSONFIN (recurrent self-organizing neural fuzzy inference network) algorithm we developed previously to detect the word boundaries in the condition of variable background noise level. In addition, a new parameter (MiFre) is proposed to estimate the varying background noise level. Based on this parameter, the noise level information used for subtractive-type speech enhancement can be estimated not only during speech pauses, but also during speech segments. This new subtractive-type enhancement scheme has been tested and found to perform well, not only in variable background noise level condition, but also in fixed background noise level condition.     

A recurrent neural fuzzy network for word boundary detection invariable noise-level environments

This paper discusses the problem of automatic word boundary detection in the presence of variable-level background noise. Commonly used robust word boundary detection algorithms always assume that the background noise level is fixed. In fact, the background noise level may vary during the procedure of recording. This is the major reason that most robust word boundary detection algorithms cannot work well in the condition of variable background noise level. In order to solve this problem, we first propose a refined time-frequency (RTF) parameter for extracting both the time and frequency features of noisy speech signals. The RTF parameter extends the (time-frequency) TF parameter proposed by Junqua et al. from single band to multiband spectrum analysis, where the frequency bands help to make the distinction between speech signal and noise clear. The RTF parameter can extract useful frequency information. Based on this RTF parameter, we further propose a new word boundary detection algorithm by using a recurrent self-organizing neural fuzzy inference network (RSONFIN). Since RSONPIN can process the temporal relations, the proposed RTF-based RSONFIN algorithm can find the variation of the background noise level and detect correct word boundaries in the condition of variable background noise level. As compared to normal neural networks, the RSONFIN can always find itself an economic network size with high-learning speed. Due to the self-learning ability of RSONFIN, this RTF-based RSONFIN algorithm avoids the need for empirically determining ambiguous decision rules in normal word boundary detection algorithms. Experimental results show that this new algorithm achieves higher recognition rate than the TF-based algorithm which has been shown to outperform several commonly used word boundary detection algorithms by about 12% in variable background noise level condition, It also reduces the recognition error rate due to endpoint detection to about 23%, compared to an average of 47% obtained by the TF-based algorithm in the same condition.     

基于模糊递归小波神经网络的葡萄酒品质预测

针对葡萄酒品质预测模型难以建立的问题,提出一种基于模糊递归小波神经网络的葡萄酒品质预测模型。利用葡萄酒物理化学指标和品酒师打分作为模型的输入输出,采用梯度下降算法在线学习隶属函数层中心、宽度和小波函数平移因子、伸缩因子、自反馈权重因子以及输出层权值。仿真实验时,首先利用Mackey-Glass混沌时间序列进行了性能测试,然后利用UCI数据集葡萄酒品质数据对所建立的品质预测模型进行了验证。结果显示,与多层感知器、径向基函数神经网络等传统前馈神经网络相比,构建的模糊递归小波神经网络品质预测模型具有更高的预测精度,更加适合于葡萄酒的品质预测。     

基于分形维数和模糊RBF神经网络的语音端点检测

简单介绍了分形维数的概念及模糊RBF神经网络的结构。利用分形维数在噪声情况下作为语音端点检测参数的优越性,组合幅度熵、帧能量及过零率作为模糊神经网络的输入参数进行语音信号端点检测。用连续语音进行非正式测试,实验证明该方法避免了选取阈值这一难点,在噪声情况下仍具有较高检测准确率。     

Identification Recurrent Type 2 Fuzzy Wavelet Neural Network and L2‐Gain Adaptive Variable Sliding Mode Robust Control of Electro‐Hydraulic Servo System (EHSS)

An electro‐hydraulic servo system (EHSS) is a kind of system with the characteristics of time‐variant, serious nonlinearity, parameter and structural uncertainty, and uncertain load disturbance in most cases. These characteristics make it very difficult to realize highly accurate control by conventional methods. In order to solve the above problems, this paper introduces a recurrent type 2 fuzzy wavelet neural network to approximate the unknown nonlinear functions of the dynamic systems through tuning by the desired adaptive law. Based on the identification by recurrent type 2 fuzzy wavelet neural network, a L2 gain design method, combining gain adaptive variable sliding mode control with H infinity control, is proposed for load disturbance, thereby accommodating uncertainties that are the main factors affecting system stability and accuracy in EHSS. In this algorithm, a recurrent type 2 fuzzy wavelet neural network is employed to evaluate the unknown dynamic characteristics of the system and gain adaptive variable sliding mode control to compensate for evaluating errors, and H infinity control to suppress the effect on system by load disturbance. The experiment results show that the proposed system L2 gain design method can make the system exhibit strong robustness to parameter variation and load disturbance.     

多特征相结合的带噪语音端点检测算法的研究

提出了一种抗噪声的端点检测新方法。针对谱熵特征对清音的检测性能以及抗噪声性能较差的缺点,结合对清音检测性能较好的短时过零率特征,以及抗噪声性能良好的美尔倒谱距离特征,实现了基于多种特征相结合的抗噪声的语音端点检测。仿真实验表明,该方法能显著提高端点检测在高噪声环境下的检测性能。     

基于C0复杂度的语音端点检测技术研究

复杂性测度的语音端点检测技术,与目前被广泛研究的短时能量、过零率、谱熵以及倒谱等技术相比较,它具有非线性技术的本质特性.实验结果表明C0复杂性测度技术可以较好地实现在动态噪声环境下对语音端点的检测.此技术的实现将有助于提高孤立字语音识别的准确率,同时也将极大的降低语音处理的计算量和复杂性.     

Prediction and identification using wavelet-based recurrent fuzzy neural networks

This paper presents a wavelet-based recurrent fuzzy neural network (WRFNN) for prediction and identification of nonlinear dynamic systems. The proposed WRFNN model combines the traditional Takagi-Sugeno-Kang (TSK) fuzzy model and the wavelet neural networks (WNN). This paper adopts the nonorthogonal and compactly supported functions as wavelet neural network bases. Temporal relations embedded in the network are caused by adding some feedback connections representing the memory units into the second layer of the feedforward wavelet-based fuzzy neural networks (WFNN). An online learning algorithm, which consists of structure learning and parameter learning, is also presented. The structure learning depends on the degree measure to obtain the number of fuzzy rules and wavelet functions. Meanwhile, the parameter learning is based on the gradient descent method for adjusting the shape of the membership function and the connection weights of WNN. Finally, computer simulations have demonstrated that the proposed WRFNN model requires fewer adjustable parameters and obtains a smaller rms error than other methods.     

Pipelined recurrent fuzzy neural networks for nonlinear adaptive speech prediction.

A class of pipelined recurrent fuzzy neural networks (PRFNNs) is proposed in this paper for nonlinear adaptive speech prediction. The PRFNNs are modular structures comprising a number of modules that are interconnected in a chained form. Each module is implemented by a small-scale recurrent fuzzy neural network (RFNN) with internal dynamics. Due to module nesting, the PRFNNs offer a number of desirable attributes, including decomposition of the modeling task, enhanced temporal processing capabilities, and multistage dynamic fuzzy inference. Tuning of the PRFNN adaptable parameters is accomplished by a series of gradient descent methods with different weighting of the modules and the decoupled extended Kalman filter (DEKF) algorithm, based on weight grouping. Extensive experimentation is carried out to evaluate the performance of the PRFNNs on the speech prediction platform. Comparative analysis shows that the PRFNNs outperform the single-RFNN models in terms of the prediction gains that are obtained and computational efficiency. Furthermore, PRFNNs provide considerably better performance compared to pipelined recurrent neural networks, for models with similar model complexity.     

Identification of control chart patterns using wavelet filtering and robust fuzzy clustering

This paper proposes a hybrid framework composed of filtering module and clustering module to identify six common types of control chart patterns, including natural pattern, cyclic pattern, upward shift, downward shift, upward trend, and downward trend. In particular, a multi-scale wavelet filter is designed for denoising and its performance is compared to single-scale filters, including mean filter and exponentially weighted moving average (EWMA) filter. Moreover, three fuzzy clustering algorithms, based on fuzzy c means (FCM), entropy fuzzy c means (EFCM) and kernel fuzzy c means (KFCM), are adopted to compare their performance of pattern classification. Experimental results demonstrate that the excellent performance of EFCM and KFCM against outliers, especially in the case of high noise level embedded in the input data. Therefore, a hybrid framework combining wavelet filter with robust fuzzy clustering is suggested and proposed in this paper. Compared to neural network based approaches, the proposed method provides a promising way for the on-line recognition of control chart patterns because of its efficient computation and robustness against outliers.     

基于小波混沌神经网络的语音识别*

基于语音信号的时变特性,提出了一种新型神经网络语音识别方法——小波混沌神经网络方法,即把小波变换和混沌特性引入到神经元,构成小波混沌神经网络,将这种神经网络用于语音识别,并与常用的BP神经网络识别方法进行了比较。实验结果表明,小波混沌神经网络的平均识别率要高于同等条件下常用的神经网络方法的识别率。