Wiley, 2011. — 450 pages. — ISBN: 978-0-470-68824-3. Spoken language understanding (SLU) is an emerging field in between speech and language processing, investigating human/ machine and human/ human communication by leveraging technologies from signal processing, pattern recognition, machine learning and artificial intelligence. SLU systems are designed to extract the meaning...
Springer, 2014. — 149 p.
Speaker verification (SV) is the process of validating the claimed identity of an individual using his/her speech. State-of-the-art SV systems perform reasonably well when the spoken utterances are ‘clean’, i.e., free from any sort of distortions caused by external factors. However, the accuracy of such systems degrade severely when speech signals are...
United Kingdom, John Wilew & Sons, Ltd. - 2013. - 496 p. Robustness techniques for ASR fall into a number of different categories. This book is divided into five parts, each focusing on a specific category of approaches. A clear understanding of robustness techniques for ASR requires a clear understanding of the principles behind automatic speech recognition and the robustness...
Prentice Hall, 2000. — 934 p. — ISBN: 0130950696, 978-0130950697. This book takes an empirical approach to language processing, based on applying statistical and other machine-learning algorithms to large corpora. Methodology boxes are included in each chapter. Each chapter is built around one or more worked examples to demonstrate the main idea of the chapter. Covers the...
Издательство Academic Press, 1986, -326 pp.
The basic problem of understanding how humans perceive information in the constant bombardment of sensory flux is, without question, one of the most difficult problems facing cognitive science. However, understanding perception is critical to developing a complete theoretical account of human information processing because perception...
Second edition. — Pearson Prentice Hall, 2009. — 988 p. With contents and search through the book. Speech and Language Processing is a general textbook on natural language processing, with an excellent coverage of the area and an unusually broad scope of topics. It includes statistical and symbolic approaches to NLP, as well as the main methods of speech processing. Regular...
Издательство Cambridge University Engineering Department, 1995. -46 pp. Most - if not all - automatic speech recognition systems explicitly or implicitly compute a score (equivalently, distance, probability, etc.) indicating how well a novel utterance matches a model of the hypothesised utterance. A fundamental problem in speech recognition is how this score may be computed,...
Издательство Wiley, 2009, -257 pp. Основные методы и алгоритмы, используемые в современных системах распознавания речи и диктора 1 Foundations Theory and Practice of Support Vector Machines Optimization From Binary Classification to Categorial Prediction 2 Acoustic Modeling A Large Margin Algorithm for Forced Alignment A Kernel Wrapper for Phoneme Sequence Recognition Augmented...
John Wiley, 2005. — 284 p. — ISBN 0-470-84407-8. This monograph was written over the past four years to serve as a text for advanced graduate students in electrical engineering interested in the techniques of automatic speech recognition and text to speech synthesis. However, the book evolved over a considerably longer period for a significantly broader purpose. Since 1972, I...
Second edition. — Pearson Prentice Hall, 2009. — 988 p. Speech and Language Processing is a general textbook on natural language processing, with an excellent coverage of the area and an unusually broad scope of topics. It includes statistical and symbolic approaches to NLP, as well as the main methods of speech processing. Regular Expressions and Automata Words and Transducers...
May 1995, School of Computer Science Carnegie Mellon University, Pittsburgh, Pennsylvania 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...
Комментарии