Plus d’un million de livres, à portée de main !
Bookbot

SpringerBriefs en Technologie de la Parole Séries

Cette série explore les avancées de pointe et les applications pratiques dans le domaine de la technologie de reconnaissance et de synthèse de la parole. Elle offre des aperçus concis mais complets des sujets de recherche actuels, comblant le fossé entre les découvertes théoriques et le déploiement dans le monde réel. Les lecteurs y trouveront des éclairages pertinents sur les méthodes de paramétrisation de la parole, le développement de systèmes de dialogue vocal et d'autres domaines critiques. Elle constitue ainsi une ressource inestimable pour les professionnels comme pour les universitaires.

Predicting Prosody from Text for Text-to-Speech Synthesis
Advances in Audio Watermarking Based on Singular Value Decomposition
Ultra Low Bit-Rate Speech Coding
Cross-Word Modeling for Arabic Speech Recognition
Language Identification Using Spectral and Prosodic Features
Language Identification Using Excitation Source Features

Ordre de lecture recommandé

  • Language Identification Using Excitation Source Features

    • 132pages
    • 5 heures de lecture

    This book discusses the contribution of excitation source information in discriminating language. The authors focus on the excitation source component of speech for enhancement of language identification (LID) performance. Language specific features are extracted using two different (i) Implicit processing of linear prediction (LP) residual and (ii) Explicit parameterization of linear prediction residual. The book discusses how in implicit processing approach, excitation source features are derived from LP residual, Hilbert envelope (magnitude) of LP residual and Phase of LP residual; and in explicit parameterization approach, LP residual signal is processed in spectral domain to extract the relevant language specific features. The authors further extract source features from these modes, which are combined for enhancing the performance of LID systems. The proposed excitation source features are also investigated for LID in background noisy environments. Each chapter of this book provides the motivation for exploring the specific feature for LID task, and subsequently discuss the methods to extract those features and finally suggest appropriate models to capture the language specific knowledge from the proposed features. Finally, the book discuss about various combinations of spectral and source features, and the desired models to enhance the performance of LID systems.

    Language Identification Using Excitation Source Features

  • Language Identification Using Spectral and Prosodic Features

    • 109pages
    • 4 heures de lecture

    This book discusses the impact of spectral features extracted from frame level, glottal closure regions, and pitch-synchronous analysis on the performance of language identification systems. In addition to spectral features, the authors explore prosodic features such as intonation, rhythm, and stress features for discriminating the languages. They present how the proposed spectral and prosodic features capture the language specific information from two complementary aspects, showing how the development of language identification (LID) system using the combination of spectral and prosodic features will enhance the accuracy of identification as well as improve the robustness of the system. This book provides the methods to extract the spectral and prosodic features at various levels, and also suggests the appropriate models for developing robust LID systems according to specific spectral and prosodic features. Finally, the book discuss about various combinations of spectral and prosodic features, and the desired models to enhance the performance of LID systems.

    Language Identification Using Spectral and Prosodic Features

  • Cross-Word Modeling for Arabic Speech Recognition

    • 74pages
    • 3 heures de lecture

    Cross-Word Modeling for Arabic Speech Recognition utilizes phonological rules in order to model the cross-word problem, a merging of adjacent words in speech caused by continuous speech, to enhance the performance of continuous speech recognition systems. The author aims to provide an understanding of the cross-word problem and how it can be avoided, specifically focusing on Arabic phonology using an HHM-based classifier.

    Cross-Word Modeling for Arabic Speech Recognition

  • Ultra Low Bit-Rate Speech Coding

    • 152pages
    • 6 heures de lecture

    "Ultra Low Bit-Rate Speech Coding" focuses on the specialized topic of speech coding at very low bit-rates of 1 Kbits/sec and less, particularly at the lower ends of this range, down to 100 bps. The authors set forth the fundamental results and trends that form the basis for such ultra low bit-rates to be viable and provide a comprehensive overview of various techniques and systems in literature to date, with particular attention to their work in the paradigm of unit-selection based segment quantization. The book is for research students, academic faculty and researchers, and industry practitioners in the areas of speech processing and speech coding.

    Ultra Low Bit-Rate Speech Coding

  • Advances in Audio Watermarking Based on Singular Value Decomposition

    • 76pages
    • 3 heures de lecture
    4,0(1)Évaluer

    This book introduces audio watermarking methods for copyright protection, which has drawn extensive attention for securing digital data from unauthorized copying. The book is divided into two parts. First, an audio watermarking method in discrete wavelet transform (DWT) and discrete cosine transform (DCT) domains using singular value decomposition (SVD) and quantization is introduced. This method is robust against various attacks and provides good imperceptible watermarked sounds. Then, an audio watermarking method in fast Fourier transform (FFT) domain using SVD and Cartesian-polar transformation (CPT) is presented. This method has high imperceptibility and high data payload and it provides good robustness against various attacks. These techniques allow media owners to protect copyright and to show authenticity and ownership of their material in a variety of applications. · Features new methods of audio watermarking for copyright protection and ownership protection · Outlines techniques that provide superior performance in terms of imperceptibility, robustness, and data payload · Includes applications such as data authentication, data indexing, broadcast monitoring, fingerprinting, etc.

    Advances in Audio Watermarking Based on Singular Value Decomposition

  • Predicting Prosody from Text for Text-to-Speech Synthesis

    • 144pages
    • 6 heures de lecture

    Predicting Prosody from Text for Text-to-Speech Synthesis covers the specific aspects of prosody, mainly focusing on how to predict the prosodic information from linguistic text, and then how to exploit the predicted prosodic knowledge for various speech applications. Author K. Sreenivasa Rao discusses proposed methods along with state-of-the-art techniques for the acquisition and incorporation of prosodic knowledge for developing speech systems. Positional, contextual and phonological features are proposed for representing the linguistic and production constraints of the sound units present in the text. This book is intended for graduate students and researchers working in the area of speech processing.

    Predicting Prosody from Text for Text-to-Speech Synthesis

  • Robust Emotion Recognition using Spectral and Prosodic Features

    • 130pages
    • 5 heures de lecture

    In this brief, the authors discuss recently explored spectral (sub-segmental and pitch synchronous) and prosodic (global and local features at word and syllable levels in different parts of the utterance) features for discerning emotions in a robust manner. The authors also delve into the complementary evidences obtained from excitation source, vocal tract system and prosodic features for the purpose of enhancing emotion recognition performance. Features based on speaking rate characteristics are explored with the help of multi-stage and hybrid models for further improving emotion recognition performance. Proposed spectral and prosodic features are evaluated on real life emotional speech corpus.

    Robust Emotion Recognition using Spectral and Prosodic Features

  • Speech Processing and Soft Computing

    • 104pages
    • 4 heures de lecture
    3,0(1)Évaluer

    Speech Processing and Soft Computing includes coverage of synergy between speech technology and bio-inspired soft computing methods. Through practical cases, the author explores, dissects and examines how soft computing may complement conventional techniques in speech enhancement and speech recognition in order to provide robust systems. The material is especially useful to graduate students and experienced researchers who are interested in expanding their horizons and investigating new research directions through review of the theoretical and practical settings of soft computing methods in very recent speech applications.

    Speech Processing and Soft Computing

  • Contemporary Methods for Speech Parameterization

    • 114pages
    • 4 heures de lecture

    Contemporary Methods for Speech Parameterization offers a general view of short-time cepstrum-based speech parameterization and provides a common ground for further in-depth studies on the subject.

    Contemporary Methods for Speech Parameterization

  • Acoustic Modeling for Emotion Recognition

    • 76pages
    • 3 heures de lecture

    This book presents state of art research in speech emotion recognition. Readers are first presented with basic research and applications – gradually more advance information is provided, giving readers comprehensive guidance for classify emotions through speech. Simulated databases are used and results extensively compared, with the features and the algorithms implemented using MATLAB. Various emotion recognition models like Linear Discriminant Analysis (LDA), Regularized Discriminant Analysis (RDA), Support Vector Machines (SVM) and K-Nearest neighbor (KNN) and are explored in detail using prosody and spectral features, and feature fusion techniques.

    Acoustic Modeling for Emotion Recognition

  • Robust Speaker Recognition in Noisy Environments

    This book discusses speaker recognition methods to deal with realistic variable noisy environments. The text covers authentication systems for; robust noisy background environments, functions in real time and incorporated in mobile devices. The book focuses on different approaches to enhance the accuracy of speaker recognition in presence of varying background environments. The authors examine: (a) Feature compensation using multiple background models, (b) Feature mapping using data-driven stochastic models, (c) Design of super vector- based GMM-SVM framework for robust speaker recognition, (d) Total variability modeling (i-vectors) in a discriminative framework and (e) Boosting method to fuse evidences from multiple SVM models.

    Robust Speaker Recognition in Noisy Environments

  • New Perspectives on Computational and Cognitive Strategies for Word Sense Disambiguation

    4,5(2)Évaluer

    Cognitive and Computational Strategies for Word Sense Disambiguation examines cognitive strategies by humans and computational strategies by machines, for WSD in parallel. Focusing on a psychologically valid property of words and senses, author Oi Yee Kwong discusses their concreteness or abstractness and draws on psycholinguistic data to examine the extent to which existing lexical resources resemble the mental lexicon as far as the concreteness distinction is concerned. The text also investigates the contribution of different knowledge sources to WSD in relation to this very intrinsic nature of words and senses.

    New Perspectives on Computational and Cognitive Strategies for Word Sense Disambiguation

  • Speech Processing in Mobile Environments

    • 133pages
    • 5 heures de lecture

    This book focuses on speech processing in the presence of low-bit rate coding and varying background environments. The methods presented in the book exploit the speech events which are robust in noisy environments. Accurate estimation of these crucial events will be useful for carrying out various speech tasks such as speech recognition, speaker recognition and speech rate modification in mobile environments. The authors provide insights into designing and developing robust methods to process the speech in mobile environments. Covering temporal and spectral enhancement methods to minimize the effect of noise and examining methods and models on speech and speaker recognition applications in mobile environments.

    Speech Processing in Mobile Environments

  • Advanced Applications of Natural Language Processing for Performing Information Extraction

    • 75pages
    • 3 heures de lecture

    This book explains how can be created information extraction (IE) applications that are able to tap the vast amount of relevant information available in natural language sources: Internet pages, official documents such as laws and regulations, books and newspapers, and social web. Readers are introduced to the problem of IE and its current challenges and limitations, supported with examples. The book discusses the need to fill the gap between documents, data, and people, and provides a broad overview of the technology supporting IE. The authors present a generic architecture for developing systems that are able to learn how to extract relevant information from natural language documents, and illustrate how to implement working systems using state-of-the-art and freely available software tools. The book also discusses concrete applications illustrating IE uses. · Provides an overview of state-of-the-art technology in information extraction (IE), discussing achievements and limitations for the software developer and providing references for specialized literature in the area · Presents a comprehensive list of freely available, high quality software for several subtasks of IE and for several natural languages · Describes a generic architecture that can learn how to extract information for a given application domain

    Advanced Applications of Natural Language Processing for Performing Information Extraction

  • Advances in Non-Linear Modeling for Speech Processing

    4,0(1)Évaluer

    Advances in Non-Linear Modeling for Speech Processing includes advanced topics in non-linear estimation and modeling techniques along with their applications to speaker recognition. Non-linear aeroacoustic modeling approach is used to estimate the important fine-structure speech events, which are not revealed by the short time Fourier transform (STFT). This aeroacostic modeling approach provides the impetus for the high resolution Teager energy operator (TEO). This operator is characterized by a time resolution that can track rapid signal energy changes within a glottal cycle. The cepstral features like linear prediction cepstral coefficients (LPCC) and mel frequency cepstral coefficients (MFCC) are computed from the magnitude spectrum of the speech frame and the phase spectra is neglected. To overcome the problem of neglecting the phase spectra, the speech production system can be represented as an amplitude modulation-frequency modulation (AM-FM) model. To demodulate the speech signal, to estimation the amplitude envelope and instantaneous frequency components, the energy separation algorithm (ESA) and the Hilbert transform demodulation (HTD) algorithm are discussed. Different features derived using above non-linear modeling techniques are used to develop a speaker identification system. Finally, it is shown that, the fusion of speech production and speech perception mechanisms can lead to a robust feature set.

    Advances in Non-Linear Modeling for Speech Processing