Posterior-thresholding feature extraction for paralinguistic speech classification

Abstract

The standard approach for handling computational paralinguistic speech tasks is to extract several thousand utterance-level features from the speech excerpts, and use machine learning methods such as Support Vector Machines and Deep Neural Networks (DNNs) for the actual classification task. In contrast, Automatic Speech Recognition handles the speech signal in small, equal-sized parts called frames. Although the speech community has developed techniques for efficient frame classification, these efforts have mostly been ignored in computational paralinguistics. In this study we propose a simple, three-step technique to utilize frame-level DNN training know-how in computational paralinguistics. We show that this method by itself provides good accuracy scores, and by combining it with the standard paralinguistic classification approach, we get close to the performance of heavyweight, state-of-the-art techniques such as Fisher vector analysis. However, our approach has the advantage that it can be easily realized by using standard speech recognition tools. To demonstrate the generic applicability of this three-step method proposed, we performed our experiments on four different corpora containing different paralinguistic tasks. Overall, we were able to achieve improvements over the baseline score in all four cases, leading to relative error reductions of up to 19%.

Objective Evaluation Method of Broadcasting Vocal Timbre Based on Feature Selection

“…From the perspective of the speech recognition model, the application of speech signal can be roughly divided into three categories, including vocal print recognition, speech recognition, and emotion recognition [8]. The classifiers for speech recognition tasks include traditional classifiers and deep learning algorithms, involving HMM, Gaussian Mixture Model (GMM), support vector machine (SVM), and extreme learning machine (ELM) [9][10][11].…”

Optimal feature selection based speech emotion recognition using two‐stream deep convolutional neural network

“…Human emotions can be automatically detected through these smarter systems by using the electroencephalography (EEG) signals, facial expression, gesture recognition, and speech signals. One of the more effective uses of speech signals is speech emotion recognition (SER), which is used to determine the emotional state of his/her speech 1–3 . Speech signals show the physiological expression that conveys the message or information about human emotions and provide an efficient communication platform among the human–computer interaction (HCI) 4 .…”

An Appraisal on Speech and Emotion Recognition Technologies based on Machine Learning

“…Digital speech processing aims at using digital computing technology to process speech signals for better understanding and increased efficiency of interaction and productive connection with speech activities. Let's look at the history of the various technologies in recent decades for speech recognition [11][12][13][14].…”

“…A conversation is being prepared to become an evolving technology that enables individuals to communicate with machines. From this point forward, it was possible to develop speech recognition software [12][13][14][15][16][17]. In 1922, the major production began.…”