Read Books Online and Download eBooks, EPub, PDF, Mobi, Kindle, Text Full Free.
Speech Signal Processing Based On Deep Learning In Complex Acoustic Environments
Download Speech Signal Processing Based On Deep Learning In Complex Acoustic Environments full books in PDF, epub, and Kindle. Read online Speech Signal Processing Based On Deep Learning In Complex Acoustic Environments ebook anywhere anytime directly on your device. Fast Download speed and no annoying ads. We cannot guarantee that every ebooks is available!
Book Synopsis Speech Signal Processing Based on Deep Learning in Complex Acoustic Environments by : Xiao-Lei Zhang
Download or read book Speech Signal Processing Based on Deep Learning in Complex Acoustic Environments written by Xiao-Lei Zhang and published by Elsevier. This book was released on 2024-09-04 with total page 282 pages. Available in PDF, EPUB and Kindle. Book excerpt: Speech Signal Processing Based on Deep Learning in Complex Acoustic Environments provides a detailed discussion of deep learning-based robust speech processing and its applications. The book begins by looking at the basics of deep learning and common deep network models, followed by front-end algorithms for deep learning-based speech denoising, speech detection, single-channel speech enhancement multi-channel speech enhancement, multi-speaker speech separation, and the applications of deep learning-based speech denoising in speaker verification and speech recognition. Provides a comprehensive introduction to the development of deep learning-based robust speech processing Covers speech detection, speech enhancement, dereverberation, multi-speaker speech separation, robust speaker verification, and robust speech recognition Focuses on a historical overview and then covers methods that demonstrate outstanding performance in practical applications
Book Synopsis Intelligent Speech Signal Processing by : Nilanjan Dey
Download or read book Intelligent Speech Signal Processing written by Nilanjan Dey and published by Academic Press. This book was released on 2019-06-15 with total page 210 pages. Available in PDF, EPUB and Kindle. Book excerpt: Intelligent Speech Signal Processing investigates the utilization of speech analytics across several systems and real-world activities, including sharing data analytics related information, creating collaboration networks between several participants, and implementing video-conferencing in different application areas. It provides a forum for readers to discover the characteristics of intelligent speech signal processing systems across different domains. Chapters focus on the latest applications of speech data analysis and management tools across different recording systems. The book emphasizes the multi-disciplinary nature of the field, presenting different applications and challenges with extensive studies on the design, implementation, development, and management of intelligent systems, neural networks, and related machine learning techniques for speech signal processing. Highlights different data analytics techniques in speech signal processing, including machine learning, and data mining Illustrates different applications and challenges across the design, implementation, and management of intelligent systems and neural networks techniques for speech signal processing Includes coverage of biomodal speech recognition, voice activity detection, spoken language and speech disorder identification, automatic speech to speech summarization, and convolutional neural networks
Book Synopsis New Era for Robust Speech Recognition by : Shinji Watanabe
Download or read book New Era for Robust Speech Recognition written by Shinji Watanabe and published by Springer. This book was released on 2017-10-30 with total page 433 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.
Book Synopsis Intelligent Speech Signal Processing by : Nilanjan Dey
Download or read book Intelligent Speech Signal Processing written by Nilanjan Dey and published by Academic Press. This book was released on 2019-03-27 with total page 209 pages. Available in PDF, EPUB and Kindle. Book excerpt: Intelligent Speech Signal Processing investigates the utilization of speech analytics across several systems and real-world activities, including sharing data analytics, creating collaboration networks between several participants, and implementing video-conferencing in different application areas. Chapters focus on the latest applications of speech data analysis and management tools across different recording systems. The book emphasizes the multidisciplinary nature of the field, presenting different applications and challenges with extensive studies on the design, development and management of intelligent systems, neural networks and related machine learning techniques for speech signal processing. Highlights different data analytics techniques in speech signal processing, including machine learning and data mining Illustrates different applications and challenges across the design, implementation and management of intelligent systems and neural networks techniques for speech signal processing Includes coverage of biomodal speech recognition, voice activity detection, spoken language and speech disorder identification, automatic speech to speech summarization, and convolutional neural networks
Book Synopsis Robust Automatic Speech Recognition by : Jinyu Li
Download or read book Robust Automatic Speech Recognition written by Jinyu Li and published by Academic Press. This book was released on 2015-10-30 with total page 308 pages. Available in PDF, EPUB and Kindle. Book excerpt: Robust Automatic Speech Recognition: A Bridge to Practical Applications establishes a solid foundation for automatic speech recognition that is robust against acoustic environmental distortion. It provides a thorough overview of classical and modern noise-and reverberation robust techniques that have been developed over the past thirty years, with an emphasis on practical methods that have been proven to be successful and which are likely to be further developed for future applications.The strengths and weaknesses of robustness-enhancing speech recognition techniques are carefully analyzed. The book covers noise-robust techniques designed for acoustic models which are based on both Gaussian mixture models and deep neural networks. In addition, a guide to selecting the best methods for practical applications is provided.The reader will: Gain a unified, deep and systematic understanding of the state-of-the-art technologies for robust speech recognition Learn the links and relationship between alternative technologies for robust speech recognition Be able to use the technology analysis and categorization detailed in the book to guide future technology development Be able to develop new noise-robust methods in the current era of deep learning for acoustic modeling in speech recognition The first book that provides a comprehensive review on noise and reverberation robust speech recognition methods in the era of deep neural networks Connects robust speech recognition techniques to machine learning paradigms with rigorous mathematical treatment Provides elegant and structural ways to categorize and analyze noise-robust speech recognition techniques Written by leading researchers who have been actively working on the subject matter in both industrial and academic organizations for many years
Book Synopsis Speech Enhancement with Improved Deep Learning Methods by : Mojtaba Hasannezhad
Download or read book Speech Enhancement with Improved Deep Learning Methods written by Mojtaba Hasannezhad and published by . This book was released on 2021 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: In real-world environments, speech signals are often corrupted by ambient noises during their acquisition, leading to degradation of quality and intelligibility of the speech for a listener. As one of the central topics in the speech processing area, speech enhancement aims to recover clean speech from such a noisy mixture. Many traditional speech enhancement methods designed based on statistical signal processing have been proposed and widely used in the past. However, the performance of these methods was limited and thus failed in sophisticated acoustic scenarios. Over the last decade, deep learning as a primary tool to develop data-driven information systems has led to revolutionary advances in speech enhancement. In this context, speech enhancement is treated as a supervised learning problem, which does not suffer from issues faced by traditional methods. This supervised learning problem has three main components: input features, learning machine, and training target. In this thesis, various deep learning architectures and methods are developed to deal with the current limitations of these three components. First, we propose a serial hybrid neural network model integrating a new low-complexity fully-convolutional convolutional neural network (CNN) and a long short-term memory (LSTM) network to estimate a phase-sensitive mask for speech enhancement. Instead of using traditional acoustic features as the input of the model, a CNN is employed to automatically extract sophisticated speech features that can maximize the performance of a model. Then, an LSTM network is chosen as the learning machine to model strong temporal dynamics of speech. The model is designed to take full advantage of the temporal dependencies and spectral correlations present in the input speech signal while keeping the model complexity low. Also, an attention technique is embedded to recalibrate the useful CNN-extracted features adaptively. Through extensive comparative experiments, we show that the proposed model significantly outperforms some known neural network-based speech enhancement methods in the presence of highly non-stationary noises, while it exhibits a relatively small number of model parameters compared to some commonly employed DNN-based methods. Most of the available approaches for speech enhancement using deep neural networks face a number of limitations: they do not exploit the information contained in the phase spectrum, while their high computational complexity and memory requirements make them unsuited for real-time applications. Hence, a new phase-aware composite deep neural network is proposed to address these challenges. Specifically, magnitude processing with spectral mask and phase reconstruction using phase derivative are proposed as key subtasks of the new network to simultaneously enhance the magnitude and phase spectra. Besides, the neural network is meticulously designed to take advantage of strong temporal and spectral dependencies of speech, while its components perform independently and in parallel to speed up the computation. The advantages of the proposed PACDNN model over some well-known DNN-based SE methods are demonstrated through extensive comparative experiments. Considering that some acoustic scenarios could be better handled using a number of low-complexity sub-DNNs, each specifically designed to perform a particular task, we propose another very low complexity and fully convolutional framework, performing speech enhancement in short-time modified discrete cosine transform (STMDCT) domain. This framework is made up of two main stages: classification and mapping. In the former stage, a CNN-based network is proposed to classify the input speech based on its utterance-level attributes, i.e., signal-to-noise ratio and gender. In the latter stage, four well-trained CNNs specialized for different specific and simple tasks transform the STMDCT of noisy input speech to the clean one. Since this framework is designed to perform in the STMDCT domain, there is no need to deal with the phase information, i.e., no phase-related computation is required. Moreover, the training target length is only one-half of those in the previous chapters, leading to lower computational complexity and less demand for the mapping CNNs. Although there are multiple branches in the model, only one of the expert CNNs is active for each time, i.e., the computational burden is related only to a single branch at anytime. Also, the mapping CNNs are fully convolutional, and their computations are performed in parallel, thus reducing the computational time. Moreover, this proposed framework reduces the latency by %55 compared to the models in the previous chapters. Through extensive experimental studies, it is shown that the MBSE framework not only gives a superior speech enhancement performance but also has a lower complexity compared to some existing deep learning-based methods.
Book Synopsis Automatic Speech Recognition by : Dong Yu
Download or read book Automatic Speech Recognition written by Dong Yu and published by Springer. This book was released on 2014-11-11 with total page 329 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.
Book Synopsis Handbook of Neural Networks for Speech Processing by : Shigeru Katagiri
Download or read book Handbook of Neural Networks for Speech Processing written by Shigeru Katagiri and published by Artech House Publishers. This book was released on 2000 with total page 560 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.
Book Synopsis Machine Learning Algorithms for Signal and Image Processing by : Deepika Ghai
Download or read book Machine Learning Algorithms for Signal and Image Processing written by Deepika Ghai and published by John Wiley & Sons. This book was released on 2022-11-18 with total page 516 pages. Available in PDF, EPUB and Kindle. Book excerpt: Machine Learning Algorithms for Signal and Image Processing Enables readers to understand the fundamental concepts of machine and deep learning techniques with interactive, real-life applications within signal and image processing Machine Learning Algorithms for Signal and Image Processing aids the reader in designing and developing real-world applications using advances in machine learning to aid and enhance speech signal processing, image processing, computer vision, biomedical signal processing, adaptive filtering, and text processing. It includes signal processing techniques applied for pre-processing, feature extraction, source separation, or data decompositions to achieve machine learning tasks. Written by well-qualified authors and contributed to by a team of experts within the field, the work covers a wide range of important topics, such as: Speech recognition, image reconstruction, object classification and detection, and text processing Healthcare monitoring, biomedical systems, and green energy How various machine and deep learning techniques can improve accuracy, precision rate recall rate, and processing time Real applications and examples, including smart sign language recognition, fake news detection in social media, structural damage prediction, and epileptic seizure detection Professionals within the field of signal and image processing seeking to adapt their work further will find immense value in this easy-to-understand yet extremely comprehensive reference work. It is also a worthy resource for students and researchers in related fields who are looking to thoroughly understand the historical and recent developments that have been made in the field.
Book Synopsis Speech and Audio Processing by : Ian Vince McLoughlin
Download or read book Speech and Audio Processing written by Ian Vince McLoughlin and published by Cambridge University Press. This book was released on 2016-07-21 with total page 403 pages. Available in PDF, EPUB and Kindle. Book excerpt: With this comprehensive and accessible introduction to the field, you will gain all the skills and knowledge needed to work with current and future audio, speech, and hearing processing technologies. Topics covered include mobile telephony, human-computer interfacing through speech, medical applications of speech and hearing technology, electronic music, audio compression and reproduction, big data audio systems and the analysis of sounds in the environment. All of this is supported by numerous practical illustrations, exercises, and hands-on MATLAB® examples on topics as diverse as psychoacoustics (including some auditory illusions), voice changers, speech compression, signal analysis and visualisation, stereo processing, low-frequency ultrasonic scanning, and machine learning techniques for big data. With its pragmatic and application driven focus, and concise explanations, this is an essential resource for anyone who wants to rapidly gain a practical understanding of speech and audio processing and technology.
Book Synopsis Convolutional and Recurrent Neural Networks for Real-time Speech Separation in the Complex Domain by : Ke Tan
Download or read book Convolutional and Recurrent Neural Networks for Real-time Speech Separation in the Complex Domain written by Ke Tan and published by . This book was released on 2021 with total page 181 pages. Available in PDF, EPUB and Kindle. Book excerpt: Speech signals are usually distorted by acoustic interference in daily listening environments. Such distortions severely degrade speech intelligibility and quality for human listeners, and make many speech-related tasks, such as automatic speech recognition and speaker identification, very difficult. The use of deep learning has led to tremendous advances in speech enhancement over the last decade. It has been increasingly important to develop deep learning based real-time speech enhancement systems due to the prevalence of many modern smart devices that require real-time processing. The objective of this dissertation is to develop real-time speech enhancement algorithms to improve intelligibility and quality of noisy speech. Our study starts by developing a strong convolutional neural network (CNN) for monaural speech enhancement. The key idea is to systematically aggregate temporal contexts through dilated convolutions, which significantly expand receptive fields. Our experimental results suggest that the proposed model consistently outperforms a feedforward deep neural network (DNN), a unidirectional long short-term memory (LSTM) model and a bidirectional LSTM model in terms of objective speech intelligibility and quality metrics. Although significant progress has been made on deep learning based speech enhancement, most existing studies only exploit magnitude-domain information and enhance the magnitude spectra. We propose to perform complex spectral mapping with a gated convolutional recurrent network (GCRN). Such an approach simultaneously enhances magnitude and phase of speech. Evaluation results show that the proposed GCRN substantially outperforms an existing CNN for complex spectral mapping. Moreover, the proposed approach yields significantly better results than magnitude spectral mapping and complex ratio masking. To achieve strong enhancement performance typically requires a large DNN, making it difficult to deploy such speech enhancement systems on devices with limited hardware resources or in applications with strict latency requirements. We propose two compression pipelines to reduce the model size for DNN-based speech enhancement. We systematically investigate these techniques and evaluate the proposed compression pipelines. Experimental results demonstrate that our approach reduces the sizes of four different models by large margins without significantly sacrificing their enhancement performance. An important application of real-time speech enhancement lies in mobile speech communication. We propose a deep learning based real-time enhancement algorithm for dual-microphone mobile phones. The proposed algorithm employs a new densely-connected convolutional recurrent network to perform dual-channel complex spectral mapping. By compressing the model with a structured pruning technique, we derive an efficient system amenable to real-time processing. Experimental results suggest that the proposed algorithm consistently outperforms an earlier algorithm to dual-channel speech enhancement for mobile phone communication, as well as a deep learning based beamformer. Multi-channel complex spectral mapping (CSM) has proven to be effective in speech separation, assuming a fixed geometry of the microphone array. We comprehensively investigate this approach, and find that multi-channel CSM achieves separation performance better than or comparable to conventional and masking-based beamforming for different array geometries and speech separation tasks. Our investigation demonstrates that this all-neural approach is a general and effective spatial filter for multi-channel speech separation.
Book Synopsis Deep Learning for Acoustic Echo Cancellation and Active Noise Control by : Hao Zhang
Download or read book Deep Learning for Acoustic Echo Cancellation and Active Noise Control written by Hao Zhang and published by . This book was released on 2022 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Acoustic echo cancellation (AEC) and active noise control (ANC) have attracted increasing attention in research and industrial applications over the past few decades. Conventionally, AEC and ANC are addressed using methods that are based on adaptive signal processing with the least mean square algorithm as the foundation. They are linear systems and do not perform satisfactorily in the presence of nonlinear distortions. However, nonlinear distortions are inevitable in applications of AEC and ANC due to the limited quality of electronic devices such as amplifiers and loudspeakers. Considering the capacity of deep learning in modeling complex nonlinear relationships, we propose deep learning approaches to address AEC and ANC problems in this dissertation. Different from traditional signal processing methods, we formulate AEC as deep learning based speech separation. The proposed approach, called deep AEC, suppresses echo and noise by separating the near-end speech from a microphone signal with the accessible far-end signal as additional information. Our study of deep AEC starts with magnitude-domain estimation, and a recurrent neural network with bidirectional long short-term memory (BLSTM) is trained to estimate a spectral magnitude mask (SMM) from the microphone and far-end signals. Later, a convolutional recurrent network (CRN) is utilized for complex spectral mapping and results in better speech quality. In addition, we explore combining deep learning based and traditional AEC algorithms to further improve AEC performance. Although deep AEC produces significant improvements over traditional AEC methods, there exists a tradeoff between echo suppression and near-end speech quality. To address this, we propose a neural cascade architecture to leverage the advantages of magnitude-domain and complex-domain estimation. The proposed cascade architecture consists of two modules. A CRN is employed in the first module for complex spectral mapping. The output is then fed as an additional input to the second module, where a long short-term memory network (LSTM) is utilized for magnitude mask estimation. The entire architecture is trained in an end-to-end manner with the two modules optimized jointly using a single loss function. This cascade architecture enables deep AEC to obtain robust magnitude estimation as well as phase enhancement. Modern communication devices are usually equipped with multiple microphones and loudspeakers. Building on deep learning based AEC in the single-channel setup, we then investigate multi-channel AEC (MCAEC) and propose a deep learning based approach named deep MCAEC. We find that the deep MCAEC approach avoids the intrinsic non-uniqueness problem in traditional MCAEC algorithms. For MCAEC setup with multiple microphones, combining deep MCAEC with supervised beamforming further improves AEC performance. For ANC, we formulate it as a supervised learning problem for the first time and propose a deep learning approach, called deep ANC, to address the nonlinear ANC problem. The main idea is to employ deep learning to encode the optimal control parameters corresponding to different noises and environments. We start with a frequency-domain method and train a CRN to estimate the real and imaginary spectrograms of the canceling signal from the reference signal so that the corresponding anti-noise can eliminate or attenuate the primary noise in the ANC system. Deep ANC is a fixed-parameter ANC approach and large-scale multi-condition training is key to achieving good generalization and robustness against a variety of noises. The proposed approach outperforms traditional ANC methods, exhibits unique advantages, and can be trained to achieve active noise cancellation no matter whether the reference signal is noise or noisy speech. The latter property could dramatically expand the scope of ANC applicability. Processing latency is a critical issue for ANC due to the causality constraint of ANC systems. Deep ANC is a frequency-domain block-based method, which incurs an algorithmic delay determined by the frame size. This delay may violate the causality constraint of ANC systems and is considered as a shortcoming of frequency-domain ANC algorithms. To address this, a time-domain method using a self-attending recurrent neural network is proposed, which allows for implementing deep ANC with smaller frame sizes. Augmented with a delay-compensated training strategy and a revised overlap-add method, the algorithmic latency of deep ANC is reduced substantially without affecting ANC performance much. Finally, we expand the single-channel deep ANC to the multi-channel setup. The resulting approach, called deep MCANC, is developed for active noise control at multiple spatial points (multi-point ANC) and within a spatial zone (generating a quiet zone). In addition, we evaluate the performance of deep MCANC under different setups and examine the impact of factors such as the number of loudspeakers and microphones, and the position of a secondary source, on MCANC performance.
Book Synopsis Speech Processing, Recognition and Artificial Neural Networks by : Gerard Chollet
Download or read book Speech Processing, Recognition and Artificial Neural Networks written by Gerard Chollet and published by Springer Science & Business Media. This book was released on 2012-12-06 with total page 352 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.
Book Synopsis Applied Speech Processing by : Nilanjan Dey
Download or read book Applied Speech Processing written by Nilanjan Dey and published by Academic Press. This book was released on 2021-01-19 with total page 208 pages. Available in PDF, EPUB and Kindle. Book excerpt: Applied Speech Processing: Algorithms and Case Studies is concerned with supporting and enhancing the utilization of speech analytics in several systems and real-world activities, including sharing data analytics related information, creating collaboration networks between several participants, and the use of video-conferencing in different application areas. The book provides a well-standing forum to discuss the characteristics of the intelligent speech signal processing systems in different domains. The book is proposed for professionals, scientists, and engineers who are involved in new techniques of intelligent speech signal processing methods and systems. It provides an outstanding foundation for undergraduate and post-graduate students as well. Includes basics of speech data analysis and management tools with several applications, highlighting recording systems Covers different techniques of big data and Internet-of-Things in speech signal processing, including machine learning and data mining Offers a multidisciplinary view of current and future challenges in this field, with extensive case studies on the design, implementation, development and management of intelligent systems, neural networks, and related machine learning techniques for speech signal processing
Book Synopsis Deep Learning Based Speech Quality Prediction by : Gabriel Mittag
Download or read book Deep Learning Based Speech Quality Prediction written by Gabriel Mittag and published by Springer Nature. This book was released on 2022-02-24 with total page 171 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book presents how to apply recent machine learning (deep learning) methods for the task of speech quality prediction. The author shows how recent advancements in machine learning can be leveraged for the task of speech quality prediction and provides an in-depth analysis of the suitability of different deep learning architectures for this task. The author then shows how the resulting model outperforms traditional speech quality models and provides additional information about the cause of a quality impairment through the prediction of the speech quality dimensions of noisiness, coloration, discontinuity, and loudness.
Book Synopsis Ocean observation based on underwater acoustic technology by : Xuebo Zhang
Download or read book Ocean observation based on underwater acoustic technology written by Xuebo Zhang and published by Frontiers Media SA. This book was released on 2023-07-04 with total page 281 pages. Available in PDF, EPUB and Kindle. Book excerpt:
Book Synopsis Neural Network Based Representation Learning and Modeling for Speech and Speaker Recognition by : Jinxi Guo
Download or read book Neural Network Based Representation Learning and Modeling for Speech and Speaker Recognition written by Jinxi Guo and published by . This book was released on 2019 with total page 127 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.
