Real-Time Robust Automatic Speech Recognition Using Compact Support Vector Machines

Abstract

Abstract-In the last years, support vector machines (SVMs) have shown excellent performance in many applications, especially in the presence of noise. In particular, SVMs offer several advantages over artificial neural networks (ANNs) that have attracted the attention of the speech processing community. Nevertheless, their high computational requirements prevent them from being used in practice in automatic speech recognition (ASR), where ANNs have proven to be successful. The high complexity of SVMs in this context arises from the use of huge speech training databases with millions of samples and highly overlapped classes. This paper suggests the use of a weighted least squares (WLS) training procedure that facilitates the possibility of imposing a compact semiparametric model on the SVM, which results in a dramatic complexity reduction. Such a complexity reduction with respect to conventional SVMs, which is between two and three orders of magnitude, allows the proposed hybrid WLS-SVC/HMM system to perform real-time speech decoding on a connected-digit recognition task (SpeechDat Spanish database). The experimental evaluation of the proposed system shows encouraging performance levels in clean and noisy conditions, although further improvements are required to reach the maturity level of current context-dependent HMM-based recognizers.

Automatic Speaker Age Estimation and Gender Dependent Emotion Recognition

“…While training the system the training dataset (T D ) is divided according to different gender dependent the age group like M Y , M A , M S , F Y , F A , F S, and also Training dataset is divided as per emotions type is the speaker speaking in the happy, sadness, disgust, fear, surprise and neutral (S, H, D, S, F, N) emotions. V is the extracted feature's vector, using the feature vector by concatenating all V create the supervector feature presentation using the SVM and GMM model for each type speaker characteristic the template will do that for you [9].…”

Integrated Speaker and Speech Recognition for Wheel Chair Movement Using Artificial Intelligence

“…Initially DNN based system are used on phone recognition task. After that DNNs are used at large scale on big vocabulary continuous speech [7][8][9][10].When DNN based systems are compared with other systems like dynamic time warping (DTW), Hidden Markov Models (HMM), Gaussian mixture models (GMM) based systems, then recognition accuracy is more for DNN based systems [11].There is fast learning in deep neural network by parameterization of weight matrix by using periodic functions. In this way training time is reduced and classification accuracy improves.…”

Nonlinear Modeling of the Inverse Force Function for the Planar Switched Reluctance Motor Using Sparse Least Squares Support Vector Machines

“…Alternatively, it has been demonstrated that support vector machines (SVMs) provide an effective approach to avoid the aforementioned problems of ANNs, which are a new machine learning method for classification and regression based on statistical learning theory and structural risk minimization principle [16]- [20]. SVMs have been effectively applied in function estimation [21]- [23], fault diagnose [24], [25], data mining [26], [27], and speech recognition [28], [29]. Furthermore, least squares support vector machines (LS-SVMs) possess faster arithmetic speed compared to SVMs [30].…”