Speaker emotion recognition is achieved through processing methods that include isolation of the speech signal and extraction of selected features for the final classification. In terms of acoustics, speech processing techniques offer extremely valuable paralinguistic information derived mainly from prosodic and spectral features. In some cases, the process is assisted by speech recognition systems, which contribute to the classification using linguistic information. Both frameworks deal with a very challenging problem, as emotional states do not have clear-cut boundaries and often differ from person to person. In this article, research papers that investigate emotion recognition from audio channels are surveyed and classified, based mostly on extracted and selected features and their classification methodology. Important topics from different classification techniques, such as databases available for experimentation, appropriate feature extraction and selection methods, classifiers and performance issues are discussed, with emphasis on research published in the last decade. This survey also provides a discussion on open trends, along with directions for future research on this topic.

Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011

Speech is an effective medium to express emotions and attitude through language. Finding the emotional content from a speech signal and identify the emotions from the speech utterances is an important task for the researchers. Speech emotion recognition has considered as an important research area over the last decade. Many researchers have been attracted due to the automated analysis of human affective behaviour. Therefore a number of systems, algorithms, and classifiers have been developed and outlined for the identification of emotional content of a speech from a person's speech. In this study, available literature on various databases, different features and classifiers have been taken in to consideration for speech emotion recognition from assorted languages.

Databases, features and classifiers for speech emotion recognition: a review

Recently, a novel learning algorithm for single-hidden-layer feedforward neural networks (SLFNs) named extreme learning machine (ELM) was proposed by Huang et al. The essence of ELM is that the learning parameters of hidden nodes, including input weights and biases, are randomly assigned and need not be tuned while the output weights can be analytically determined by the simple generalized inverse operation. The only parameter needed to be defined is the number of hidden nodes. Compared with other traditional learning algorithms for SLFNs, ELM provides extremely faster learning speed, better generalization performance and with least human intervention. This paper firstly introduces a brief review of ELM, describing the principle and algorithm of ELM. Then, we put emphasis on the improved methods or the typical variants of ELM, especially on incremental ELM, pruning ELM, error-minimized ELM, two-stage ELM, online sequential ELM, evolutionary ELM, voting-based ELM, ordinal ELM, fully complex ELM, and symmetric ELM. Next, the paper summarized the applications of ELM on classification, regression, function approximation, pattern recognition, forecasting and diagnosis, and so on. In the last, the paper discussed several open issues of ELM, which may be worthy of exploring in the future.

Extreme learning machine and its applications

An extreme learning machine (ELM) is a feedforward neural network (FNN) like learning system whose connections with output neurons are adjustable, while the connections with and within hidden neurons are randomly fixed. Numerous applications have demonstrated the feasibility and high efficiency of ELM-like systems. It has, however, been open if this is true for any general applications. In this two-part paper, we conduct a comprehensive feasibility analysis of ELM. In Part I, we provide an answer to the question by theoretically justifying the following: 1) for some suitable activation functions, such as polynomials, Nadaraya-Watson and sigmoid functions, the ELM-like systems can attain the theoretical generalization bound of the FNNs with all connections adjusted, i.e., they do not degrade the generalization capability of the FNNs even when the connections with and within hidden neurons are randomly fixed; 2) the number of hidden neurons needed for an ELM-like system to achieve the theoretical bound can be estimated; and 3) whenever the activation function is taken as polynomial, the deduced hidden layer output matrix is of full column-rank, therefore the generalized inverse technique can be efficiently applied to yield the solution of an ELM-like system, and, furthermore, for the nonpolynomial case, the Tikhonov regularization can be applied to guarantee the weak regularity while not sacrificing the generalization capability. In Part II, however, we reveal a different aspect of the feasibility of ELM: there also exists some activation functions, which makes the corresponding ELM degrade the generalization capability. The obtained results underlie the feasibility and efficiency of ELM-like systems, and yield various generalizations and improvements of the systems as well.

Is Extreme Learning Machine Feasible? A Theoretical Assessment (Part I)

Conventional extreme learning machines (ELMs) solve a Moore–Penrose generalized inverse of hidden layer activated matrix and analytically determine the output weights to achieve generalized performance, by assuming the same loss from different types of misclassification. The assumption may not hold in cost-sensitive recognition tasks, such as face recognition-based access control system, where misclassifying a stranger as a family member may result in more serious disaster than misclassifying a family member as a stranger. Though recent cost-sensitive learning can reduce the total loss with a given cost matrix that quantifies how severe one type of mistake against another, in many realistic cases, the cost matrix is unknown to users. Motivated by these concerns, this paper proposes an evolutionary cost-sensitive ELM, with the following merits: 1) to the best of our knowledge, it is the first proposal of ELM in evolutionary cost-sensitive classification scenario; 2) it well addresses the open issue of how to define the cost matrix in cost-sensitive learning tasks; and 3) an evolutionary backtracking search algorithm is induced for adaptive cost matrix optimization. Experiments in a variety of cost-sensitive tasks well demonstrate the effectiveness of the proposed approaches, with about 5%–10% improvements.

Evolutionary Cost-Sensitive Extreme Learning Machine

This paper deals with the recognition of handwritten Malayalam character using wavelet energy feature (WEF) and extreme learning machine (ELM). The wavelet energy (WE) is a new and robust parameter, and is derived using wavelet transform. It can reduce the influences of different types of noise at different levels. WEF can reflect the WE distribution of characters in several directions at different scales. To a non oscillating pattern, the amplitudes of wavelet coefficients increase when the scale of wavelet decomposition increase. WE of different decomposition levels have different powers to discriminate the character images. These features constitute patterns of handwritten characters for classification. The traditional learning algorithms of the different classifiers are far slower than required. So we have used an extremely fast leaning algorithm called ELM for single hidden layer feed forward networks (SLFN), which randomly chooses the input weights and analytically determines the output weights of SLFN. This algorithm learns much faster than traditional popular learning algorithms for feed forward neural networks. This feature vector, classifier combination gave good recognition accuracy at level 6 of the wavelet decomposition.

Handwritten character recognition using wavelet energy and extreme learning machine

This paper explains a study conducted based on wavelet based transform techniques. We have used discrete wavelet transform and wavelet packet decomposition. The database is created by using Malayalam (one of the south Indian Languages) language spoken words. Daubechies type of mother wavelet was used for the experiment. Six hundred and forty samples are collected, for the experiment. The feature vector was produced for all words and formed a training set for classification and recognition purpose. A sequence of wavelet decomposition levels were carried out to achieve a good feature vector. Feature vectors of element size twelve and eight were collected for all the words by using discrete wavelet transform and wavelet packet decomposition techniques respectively. Results are also prepared for the comparison of the signal at each decomposition level. The physical changes that are occurred during each decomposition levels could be observed from the results.

Features of Wavelet Packet Decomposition and Discrete Wavelet Transform for Malayalam Speech Recognition

This paper deals a novel speech feature extraction technique based on wavelet. We have employed daubechies 4 type of wavelet for feature extraction. Artificial neural network technique (ANN) is used for classification and recognition purpose. We have used five Malayalam (one of the South Indian languages) words for the experiment. One hundred and sixty samples are collected, categorized labeled and stored in a database. The feature vector is produced for all words and formed a training set for classification and recognition purpose. A sequence of decomposition levels are carried out to achieve a good feature vector. A feature vector of element size twelve is collected for all words at the eighth level of decomposition. A graph is also prepared for the comparison of the signal at each decomposition level. From that graph we can understand the physical changes that are occurred during the decomposition. By using this method we have achieved a recognition rate of 89%.

Speech Recognition of Isolated Malayalam Words Using Wavelet Features and Artificial Neural Network

Automatic Emotion Recognition (AER) from speech is one of the most interested research domains for the scientific world. AER simply means to make a machine able to recognize the different emotions from speech. We have created and analyzed an elicited database consisting of 700 utterances under four different emotional classes such as neutral happy sad and anger. Malayalam (One of the south Indian languages) was used to conduct the experiment. We have used a database proportion of 80:20 for the training and testing purpose. We have analyzed the emotional speech corpus recorded by using both Discrete Wavelet Transforms (DWTs) and Mel Frequency Cepstral Coefficients (MFCCs) and obtained an overall recognition accuracy of 68.5% and 55% respectively. Artificial Neural Network was used for the classification and recognition purpose.

Speaker Independent Automatic Emotion Recognition from Speech: A Comparison of MFCCs and Discrete Wavelet Transforms

It is essential to detect partial discharge (PD) as a symptom of insulation breakdown in high voltage (HV) applications. However accuracy of such measurement is often degraded due to the existence of noise in the signal. Wavelet Transform (WT) seems to be more suitable than traditional Fourier Transform in analyzing signals with interesting transient information such as partial discharge (PD) signals. In this paper a WT method with soft thresholding is used for signal denoising. PD signals and corona obtained from actual measurements with different voltage magnitudes are processed. Processed signals show the better result.

V. Krishnan

Papers

Handwritten character recognition using wavelet energy and extreme learning machine

Features of Wavelet Packet Decomposition and Discrete Wavelet Transform for Malayalam Speech Recognition

Speech Recognition of Isolated Malayalam Words Using Wavelet Features and Artificial Neural Network

Speaker Independent Automatic Emotion Recognition from Speech: A Comparison of MFCCs and Discrete Wavelet Transforms

Removal of Interferences from Partial Discharge Pulses using Wavelet Transform