Neural Network Based Representation Learning And Modeling For Speech And Speaker Recognition

Deep learning and neural network research has grown significantly in the fields of automatic speech recognition (ASR) and speaker recognition. Compared to traditional methods, deep learning-based approaches are more powerful in learning representation from data and building complex models. In this dissertation, we focus on representation learning and modeling using neural network-based approaches for speech and speaker recognition. In the first part of the dissertation, we present two novel neural network-based methods to learn speaker-specific and phoneme-invariant features for short-utterance speaker verification. We first propose to learn a spectral feature mapping from each speech signal to the corresponding subglottal acoustic signal which has less phoneme variation, using deep neural networks (DNNs). The estimated subglottal features show better speaker-separation ability and provide complementary information when combined with traditional speech features on speaker verification tasks. Additional, we propose another DNN-based mapping model, which maps the speaker representation extracted from short utterances to the speaker representation extracted from long utterances of the same speaker. Two non-linear regression models using an autoencoder are proposed to learn this mapping, and they both improve speaker verification performance significantly. In the second part of the dissertation, we design several new neural network models which take raw speech features (either complex Discrete Fourier Transform (DFT) features or raw waveforms) as input, and perform the feature extraction and phone classification jointly. We first propose a unified deep Highway (HW) network with a time-delayed bottleneck layer (TDB), in the middle, for feature extraction. The TDB-HW networks with complex DFT features as input provide significantly lower error rates compared with hand-designed spectrum features on large-scale keyword spotting tasks. Next, we present a 1-D Convolutional Neural Network (CNN) model, which takes raw waveforms as input and uses convolutional layers to do hierarchical feature extraction. The proposed 1-D CNN model outperforms standard systems with hand-designed features. In order to further reduce the redundancy of the 1-D CNN model, we propose a filter sampling and combination (FSC) technique, which can reduce the model size by 70% and still improve the performance on ASR tasks. In the third part of dissertation, we propose two novel neural-network models for sequence modeling. We first propose an attention mechanism for acoustic sequence modeling. The attention mechanism can automatically predict the importance of each time step and select the most important information from sequences. Secondly, we present a sequence-to-sequence based spelling correction model for end-to-end ASR. The proposed correction model can effectively correct errors made by the ASR systems.

Speech Processing, Recognition and Artificial Neural Networks contains papers from leading researchers and selected students, discussing the experiments, theories and perspectives of acoustic phonetics as well as the latest techniques in the field of spe ech science and technology. Topics covered in this book include; Fundamentals of Speech Analysis and Perceptron; Speech Processing; Stochastic Models for Speech; Auditory and Neural Network Models for Speech; Task-Oriented Applications of Automatic Speech Recognition and Synthesis.

What Is Speech Recognition Computer science and computational linguistics include a subfield called speech recognition that focuses on the development of approaches and technologies that enable computers to recognize spoken language and translate it into text. Speech recognition is an interdisciplinary subfield of computer science. It is also known as computer speech recognition (CSR) and speech to text (STT). Another name for it is automatic speech recognition (ASR). The domains of computer science, linguistics, and computer engineering are all represented in its incorporation of knowledge and study. Speech synthesis is the process of doing things backwards. How You Will Benefit (I) Insights, and validations about the following topics: Chapter 1: Speech recognition Chapter 2: Computational linguistics Chapter 3: Natural language processing Chapter 4: Speech processing Chapter 5: Pattern recognition Chapter 6: Language model Chapter 7: Deep learning Chapter 8: Recurrent neural network Chapter 9: Long short-term memory Chapter 10: Voice computing (II) Answering the public top questions about speech recognition. (III) Real world examples for the usage of speech recognition in many fields. (IV) 17 appendices to explain, briefly, 266 emerging technologies in each industry to have 360-degree full understanding of speech recognition' technologies. Who This Book Is For Professionals, undergraduate and graduate students, enthusiasts, hobbyists, and those who want to go beyond basic knowledge or information for any kind of speech recognition.

This book will help readers understand fundamental and advanced statistical models and deep learning models for robust speaker recognition and domain adaptation. This useful toolkit enables readers to apply machine learning techniques to address practical issues, such as robustness under adverse acoustic environments and domain mismatch, when deploying speaker recognition systems. Presenting state-of-the-art machine learning techniques for speaker recognition and featuring a range of probabilistic models, learning algorithms, case studies, and new trends and directions for speaker recognition based on modern machine learning and deep learning, this is the perfect resource for graduates, researchers, practitioners and engineers in electrical engineering, computer science and applied mathematics.

This book provides a comprehensive overview of the recent advancement in the field of automatic speech recognition with a focus on deep learning models including deep neural networks and many of their variants. This is the first automatic speech recognition book dedicated to the deep learning approach. In addition to the rigorous mathematical treatment of the subject, the book also presents insights and theoretical foundation of a series of highly successful deep learning models.

This book covers the state-of-the-art in deep neural-network-based methods for noise robustness in distant speech recognition applications. It provides insights and detailed descriptions of some of the new concepts and key technologies in the field, including novel architectures for speech enhancement, microphone arrays, robust features, acoustic model adaptation, training data augmentation, and training criteria. The contributed chapters also include descriptions of real-world applications, benchmark tools and datasets widely used in the field. This book is intended for researchers and practitioners working in the field of speech processing and recognition who are interested in the latest deep learning techniques for noise robustness. It will also be of interest to graduate students in electrical engineering or computer science, who will find it a useful guide to this field of research.

Here are the comprehensive details on cutting edge technologies employing neural networks for speech recognition and speech processing in modern communications. Going far beyond the simple speech recognition technologies on the market today, this new book, written by and for speech and signal processing engineers in industry, R&D, and academia, takes you to the forefront of the hottest emergent neural net-based speech processing techniques.

This book discusses large margin and kernel methods for speech and speaker recognition Speech and Speaker Recognition: Large Margin and Kernel Methods is a collation of research in the recent advances in large margin and kernel methods, as applied to the field of speech and speaker recognition. It presents theoretical and practical foundations of these methods, from support vector machines to large margin methods for structured learning. It also provides examples of large margin based acoustic modelling for continuous speech recognizers, where the grounds for practical large margin sequence learning are set. Large margin methods for discriminative language modelling and text independent speaker verification are also addressed in this book. Key Features: Provides an up-to-date snapshot of the current state of research in this field Covers important aspects of extending the binary support vector machine to speech and speaker recognition applications Discusses large margin and kernel method algorithms for sequence prediction required for acoustic modeling Reviews past and present work on discriminative training of language models, and describes different large margin algorithms for the application of part-of-speech tagging Surveys recent work on the use of kernel approaches to text-independent speaker verification, and introduces the main concepts and algorithms Surveys recent work on kernel approaches to learning a similarity matrix from data This book will be of interest to researchers, practitioners, engineers, and scientists in speech processing and machine learning fields.

Abstract: "This thesis examines how artificial neural networks can benefit a large vocabulary, speaker independent, continuous speech recognition system. Currently, most speech recognition systems are based on hidden Markov models (HMMs), a statistical framework that supports both acoustic and temporal modeling. Despite their state-of-the-art performance, HMMs make a number of suboptimal modeling assumptions that limit their potential effectiveness. Neural networks avoid many of these assumptions, while they can also learn complex functions, generalize effectively, tolerate noise, and support parallelism. While neural networks can readily be applied to acoustic modeling, it is not yet clear how they can be used for temporal modeling. Therefore, we explore a class of systems called NN-HMM hybrids, in which neural networks perform acoustic modeling, and HMMs perform temporal modeling. We argue that a NN-HMM hybrid has several theoretical advantages over a pure HMM system, including better acoustic modeling accuracy, better context sensitivity, more natural discrimination, and a more economical use of parameters. These advantages are confirmed experimentally by a NN-HMM hybrid that we developed, based on context-independent phoneme models, that achieved 90.5% word accuracy on the Resource Management database, in contrast to only 86.0% accuracy achieved by a pure HMM under similar conditions. In the course of developing this system, we explored two different ways to use neural networks for acoustic modeling: prediction and classification. We found that predictive networks yield poor results because of a lack of discrimination, but classification networks gave excellent results. We verified that, in accordance with theory, the output activations of a classification network form highly accurate estimates of the posterior probabilities P(class/input), and we showed how these can easily be converted to likelihoods P(input/class) for standard HMM recognition algorithms. Finally, this thesis reports how we optimized the accuracy of our system with many natural techniques, such as expanding the input window size, normalizing the inputs, increasing the number of hidden units, converting the network's output activations to log likelihoods, optimizing the learning rate schedule by automatic search, backpropagating error from word level outputs, and using gender dependent networks."