This book constitutes the refereed proceedings of the 15th International Conference on Speech and Computer, SPECOM 2013, held in Pilsen, Czech Republic. The 48 revised full papers presented were carefully reviewed and selected from 90 initial submissions. The papers are organized in topical sections on speech recognition and understanding, spoken language processing, spoken dialogue systems, speaker identification and diarization, speech forensics and security, language identification, text-to-speech systems, speech perception and speech disorders, multimodal analysis and synthesis, understanding of speech and text, and audio-visual speech processing.

Design and build innovative, custom, data-driven Alexa skills for home or business. Working through several projects, this book teaches you how to build Alexa skills and integrate them with online APIs. If you have basic Python skills, this book will show you how to build data-driven Alexa skills. You will learn to use data to give your Alexa skills dynamic intelligence, in-depth knowledge, and the ability to remember. Data-Driven Alexa Skills takes a step-by-step approach to skill development. You will begin by configuring simple skills in the Alexa Skill Builder Console. Then you will develop advanced custom skills that use several Alexa Skill Development Kit features to integrate with lambda functions, Amazon Web Services (AWS), and Internet data feeds. These advanced skills enable you to link user accounts, query and store data using a NoSQL database, and access real estate listings and stock prices via web APIs. What You Will Learn Set up and configure your development environment properly the first time Build Alexa skills quickly and efficiently using Agile tools and techniques Create a variety of data-driven Alexa skills for home and business Access data from web applications and Internet data sources via their APIs Test with unit-testing frameworks throughout the development life cycle Manage and query your data using the DynamoDb NoSQL database engines Who This Book Is For Developers who wish to go beyond Hello World and build complex, data-driven applications on Amazon's Alexa platform; developers who want to learn how to use Lambda functions, the Alexa Skills SDK, Alexa Presentation Language, and Alexa Conversations; developers interested in integrating with public APIs such as real estate listings and stock market prices. Readers will need to have basic Python skills.

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.

Unleash your iPod touch and take it to the limit using secret tips and techniques. Fast and fun to read, Taking Your iPod touch 5 to the Max will help you get the most out of iOS 5 on your iPod touch. You'll find all the best undocumented tricks, as well as the most efficient and enjoyable introduction to the iPod touch available. Starting with the basics, you'll quickly move on to discover the iPod touch's hidden potential, like how to connect to a TV and get contract-free VoIP. From e-mail and surfing the Web, to using iTunes, iBooks, games, photos, ripping DVDs and getting free VoIP with Skype or FaceTime--whether you have a new iPod touch, or an older iPod touch with iOS 5, you'll find it all in this book. You'll even learn tips on where to get the best and cheapest iPod touch accessories. Get ready to take iPod touch to the max What you'll learn * How to get your music, videos, and data onto your iPod touch * How to manage your media * Tips for shopping in the App Store and iTunes Store * Getting the most out of iBooks * Using Mail on your iPod touch * Keeping in touch with FaceTime Who this book is for Anyone who wants to get the most out of their iPod touch 5.Table of Contents * Bringing Home the iPod touch * Putting Your Data and Media on the iPod touch * Interacting with Your iPod touch * Browsing with Wi-fi and Safari * Touching Photos and Videos * Touching Your Music * Shopping at the iTunes Store * Shopping at the App Store * Reading and Buying Books with iBooks * Setting Up and Using Mail * Staying on Time and Getting There * Using your Desk Set * Photographing and Recording the World Around You * Video Calling with FaceTime * Customizing Your iPod touch

Automatic speech recognition (ASR) systems are finding increasing use in everyday life. Many of the commonplace environments where the systems are used are noisy, for example users calling up a voice search system from a busy cafeteria or a street. This can result in degraded speech recordings and adversely affect the performance of speech recognition systems. As the use of ASR systems increases, knowledge of the state-of-the-art in techniques to deal with such problems becomes critical to system and application engineers and researchers who work with or on ASR technologies. This book presents a comprehensive survey of the state-of-the-art in techniques used to improve the robustness of speech recognition systems to these degrading external influences.

Key features: Reviews all the main noise robust ASR approaches, including signal separation, voice activity detection, robust feature extraction, model compensation and adaptation, missing data techniques and recognition of reverberant speech.Acts as a timely exposition of the topic in light of more widespread use in the future of ASR technology in challenging environments.Addresses robustness issues and signal degradation which are both key requirements for practitioners of ASR.Includes contributions from top ASR researchers from leading research units in the field

We are surrounded by noise; we must be able to separate the signals we want to hear from those we do not. To overcome this 'cocktail party effect' we have developed various strategies; endowing computers with similar abilities would enable the development of devices such as intelligent hearing aids and robust speech recognition systems. This book describes a system which attempts to separate multiple, simultaneous acoustic sources using strategies based on those used by humans. It is both a review of recent work on the modelling of auditory processes, and a presentation of a new model in which acoustic signals are decomposed into elements. These structures are then re-assembled in accordance with rules of auditory organisation which operate to bind together elements that are likely to have arisen from the same source. The model is evaluated by measuring its ability to separate speech from a wide variety of other sounds, including music, phones and other speech.

Cutting-edge perspectives on a hot topic, with few competing titles on the market Contributor list includes some very well known professionals, as well as diverse academics from different disciplines Accessible and interdisciplinary introductory volume

Strike a balance between theory and practice! With this text, you'll, find a balance between theory and practice that allows you to build your understanding of the basic concepts, assumptions, and limitations of the theory of speech analysis and synthesis. The methods for data analysis as well as the theoretical background are provided to help you comprehend the analysis results. And you'll be able to study the features and properties of speech as a signal without having to record data and write software to analyze the data. The text includes two CDs that contain stand-alone and MATLAB software and speech and electroglottographic data. The CDs illustrate the effects that speech models and speech analysis procedures have on the quality of synthesized speech. An extensive speech database provides numerous speech files and other data. Examples included in each chapter demonstrate how to use the software. The CDs allow you to:
* Calculate the parameters of linear prediction speech models.
* Examine procedures for converting the speech of one speaker to sound like that of another speaker (i.e., voice conversion).
* Analyze and alter the temporal structure of the speech signal. This allows you to automatically parse speech into various features, such as voiced segments, unvoiced segments, nasal and non-nasal segments, fricatives, stops, and more.
* Create speech with a "high speaking rate" or generate speech with a "slow speaking rate."
* Adjust the parameters of the vocal fold model to change the vocal fold tension, length, thickness, mass, etc., in order to observe the effects of these parameters on the vibratory motion of the vocal folds.

This work addresses this problem in the short-time Fourier transform (STFT) domain. We divide the general problem into five basic categories depending on the number of microphones being used and whether the interframe or interband correlation is considered. The first category deals with the single-channel problem where STFT coefficients at different frames and frequency bands are assumed to be independent. In this case, the noise reduction filter in each frequency band is basically a real gain. Since a gain does not improve the signal-to-noise ratio (SNR) for any given subband and frame, the noise reduction is basically achieved by liftering the subbands and frames that are less noisy while weighing down on those that are more noisy. The second category also concerns the single-channel problem. The difference is that now the interframe correlation is taken into account and a filter is applied in each subband instead of just a gain. The advantage of using the interframe correlation is that we can improve not only the long-time fullband SNR, but the frame-wise subband SNR as well. The third and fourth classes discuss the problem of multichannel noise reduction in the STFT domain with and without interframe correlation, respectively. In the last category, we consider the interband correlation in the design of the noise reduction filters. We illustrate the basic principle for the single-channel case as an example, while this concept can be generalized to other scenarios. In all categories, we propose different optimization cost functions from which we derive the optimal filters and we also define the performance measures that help analyzing them.

"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.

Music is much more than listening to audio encoded in some unreadable binary format. It is, instead, an adventure similar to reading a book and entering its world, complete with a story, plot, sound, images, texts, and plenty of related data with, for instance, historical, scientific, literary, and musicological contents. Navigation of this world, such as that of an opera, a jazz suite and jam session, a symphony, a piece from non-Western culture, is possible thanks to the specifications of new standard IEEE 1599, "IEEE Recommended Practice for Defining a Commonly Acceptable Musical Application Using XML," which uses symbols in language XML and music layers to express all its multimedia characteristics. Because of its encompassing features, this standard allows the use of existing audio and video standards, as well as recuperation of material in some old format, the events of which are managed by a single XML file, which is human and machine readable - musical symbols have been read by humans for at least forty centuries.

Anyone wanting to realize a computer application using IEEE 1599 -- music and computer science departments, computer generated music research laboratories (e.g. CCRMA at Stanford, CNMAT at Berkeley, and IRCAM in Paris), music library conservationists, music industry frontrunners (Apple, TDK, Yamaha, Sony), etc. -- will need this first book-length explanation of the new standard as a reference.

The book will include a manual teaching how to encode music with IEEE 1599 as an appendix, plus a CD-R with a video demonstrating the applications described in the text and actual sample applications that the user can load onto his or her PC and experiment with.

Go beyond HTML5's Audio tag and boost the audio capabilities of your web application with the Web Audio API. Packed with lots of code examples, crisp descriptions, and useful illustrations, this concise guide shows you how to use this JavaScript API to make the sounds and music of your games and interactive applications come alive. You need little or no digital audio expertise to get started. Author Boris Smus introduces you to digital audio concepts, then shows you how the Web Audio API solves specific application audio problems. You'll not only learn how to synthesize and process digital audio, you'll also explore audio analysis and visualization with this API. Learn Web Audio API, including audio graphs and the audio nodes Provide quick feedback to user actions by scheduling sounds with the API's precise timing model Control gain, volume, and loudness, and dive into clipping and crossfading Understand pitch and frequency: use tools to manipulate soundforms directly with JavaScript Generate synthetic sound effects and learn how to spatialize sound in 3D space Use Web Audio API with the Audio tag, getUserMedia, and the Page Visibility API

Pure Data (Pd) is a graphical programming environment for audio and more; libpd is a wrapper that turns Pd into a portable, embeddable audio library. Brian Eno's soundtrack of the game Spore is generated by Pure Data. Inception The App is based on libpd and has been downloaded more than three million times. The popular RJDJ also uses the technology. The purpose of this book is to present tools and techniques for using Pure Data and libpd as an audio engine in mobile apps (for Android and iOS). The tools described are perfect for the sound engine for a game or for transforming a phone or tablet into an experimental instrument. After reading the book, audio developers will know how to prepare Pd patches for use with libpd, and app developers will know how to use all features of the libpd API. Readers with some experience in both computer music and mobile development will be able to create complete musical apps. The book includes a crash course in Pd, just enough to allow readers to make sounds and control them, as well as a discussion of existing solutions for rapidly deploying Pd patches to mobile devices. An introduction to Android or iOS development is beyond the scope of this book; readers will be expected to have a basic grasp of their platform of choice, including a working development setup. The book will, however, explain how to integrate libpd into an existing setup. A number of sample apps, ranging from minimal to full featured, for both Android and iOS, will illustrate all major points.

Below the level of the musical note lies the realm of microsound, of sound particles lasting less than one-tenth of a second. Recent technological advances allow us to probe and manipulate these pinpoints of sound, dissolving the traditional building blocks of music -- notes and their intervals -- into a more fluid and supple medium. The sensations of point, pulse (series of points), line (tone), and surface (texture) emerge as particle density increases. Sounds coalesce, evaporate, and mutate into other sounds.Composers have used theories of microsound in computer music since the 1950s. Distinguished practitioners include Karlheinz Stockhausen and Iannis Xenakis. Today, with the increased interest in computer and electronic music, many young composers and software synthesis developers are exploring its advantages. Covering all aspects of composition with sound particles, Microsound offers composition theory, historical accounts, technical overviews, acoustical experiments, descriptions of musical works, and aesthetic reflections. The book is accompanied by an audio CD of examples.

This book offers an overview of audio processing, including the latest advances in the methodologies used in audio processing and speech recognition. First, it discusses the importance of audio indexing and classical information retrieval problem and presents two major indexing techniques, namely Large Vocabulary Continuous Speech Recognition (LVCSR) and Phonetic Search. It then offers brief insights into the human speech production system and its modeling, which are required to produce artificial speech. It also discusses various components of an automatic speech recognition (ASR) system. Describing the chronological developments in ASR systems, and briefly examining the statistical models used in ASR as well as the related mathematical deductions, the book summarizes a number of state-of-the-art classification techniques and their application in audio/speech classification. By providing insights into various aspects of audio/speech processing and speech recognition, this book appeals a wide audience, from researchers and postgraduate students to those new to the field.

Understanding Video Game Music develops a musicology of video game music by providing methods and concepts for understanding music in this medium. From the practicalities of investigating the video game as a musical source to the critical perspectives on game music - using examples including Final Fantasy VII, Monkey Island 2, SSX Tricky and Silent Hill - these explorations not only illuminate aspects of game music, but also provide conceptual ideas valuable for future analysis. Music is not a redundant echo of other textual levels of the game, but central to the experience of interacting with video games. As the author likes to describe it, this book is about music for racing a rally car, music for evading zombies, music for dancing, music for solving puzzles, music for saving the Earth from aliens, music for managing a city, music for being a hero; in short, it is about music for playing.

Selling Digital Music, Formatting Culture documents the transition of recorded music on CDs to music as digital files on computers. More than two decades after the first digital music files began circulating in online archives and playing through new software media players, we have yet to fully internalize the cultural and aesthetic consequences of these shifts. Tracing the emergence of what Jeremy Wade Morris calls the "digital music commodity," Selling Digital Music, Formatting Culture considers how a conflicted assemblage of technologies, users, and industries helped reformat popular music's meanings and uses. Through case studies of five key technologies - Winamp, metadata, Napster, iTunes, and cloud computing - this book explores how music listeners gradually came to understand computers and digital files as suitable replacements for their stereos and CD. Morris connects industrial production, popular culture, technology, and commerce in a narrative involving the aesthetics of music and computers, and the labor of producers and everyday users, as well as the value that listeners make and take from digital objects and cultural goods. Above all, Selling Digital Music, Formatting Culture is a sounding out of music's encounters with the interfaces, metadata, and algorithms of digital culture and of why the shifting form of the music commodity matters for the music and other media we love.

With this comprehensive guide you will learn how to apply Bayesian machine learning techniques systematically to solve various problems in speech and language processing. A range of statistical models is detailed, from hidden Markov models to Gaussian mixture models, n-gram models and latent topic models, along with applications including automatic speech recognition, speaker verification, and information retrieval. Approximate Bayesian inferences based on MAP, Evidence, Asymptotic, VB, and MCMC approximations are provided as well as full derivations of calculations, useful notations, formulas, and rules. The authors address the difficulties of straightforward applications and provide detailed examples and case studies to demonstrate how you can successfully use practical Bayesian inference methods to improve the performance of information systems. This is an invaluable resource for students, researchers, and industry practitioners working in machine learning, signal processing, and speech and language processing.

We live in a society which is increasingly interconnected, in which communication between individuals is mostly mediated via some electronic platform, and transactions are often carried out remotely. In such a world, traditional notions of trust and confidence in the identity of those with whom we are interacting, taken for granted in the past, can be much less reliable. Biometrics - the scientific discipline of identifying individuals by means of the measurement of unique personal attributes - provides a reliable means of establishing or confirming an individual's identity. These attributes include facial appearance, fingerprints, iris patterning, the voice, the way we write, or even the way we walk. The new technologies of biometrics have a wide range of practical applications, from securing mobile phones and laptops to establishing identity in bank transactions, travel documents, and national identity cards. This Very Short Introduction considers the capabilities of biometrics-based identity checking, from first principles to the practicalities of using different types of identification data. Michael Fairhurst looks at the basic techniques in use today, ongoing developments in system design, and emerging technologies, all aimed at improving precision in identification, and providing solutions to an increasingly wide range of practical problems. Considering how they may continue to develop in the future, Fairhurst explores the benefits and limitations of these pervasive and powerful technologies, and how they can effectively support our increasingly interconnected society. ABOUT THE SERIES: The Very Short Introductions series from Oxford University Press contains hundreds of titles in almost every subject area. These pocket-sized books are the perfect way to get ahead in a new subject quickly. Our expert authors combine facts, analysis, perspective, new ideas, and enthusiasm to make interesting and challenging topics highly readable.

Die Optimierung des Web-Auftritts ist fur Entscheider und Mediengestalter ein wesentliches Ziel ihrer Tatigkeit. Anhand von Erkenntnissen der Ergonomie und Arbeitswissenschaft erklart der Autor, was Besucher auf Internetseiten fesselt und zum Kauf anregt, aber auch, was abschreckt. Fur die Planung eines erfolgreichen E-Business-Auftritts vermittelt das Buch wichtige Grundsatze. Fur das Design einer Informationsseite werden Internet-spezifische Prasentationsregeln erlautert, deren Ziel ein Internet-Auftritt ist. Ein Uberblick uber die grundlegenden Internet-Konzepte rundet das Werk ab."

An examination of the many complex aspects of game audio, from the perspectives of both sound design and music composition. A distinguishing feature of video games is their interactivity, and sound plays an important role in this: a player's actions can trigger dialogue, sound effects, ambient sound, and music. And yet game sound has been neglected in the growing literature on game studies. This book fills that gap, introducing readers to the many complex aspects of game audio, from its development in early games to theoretical discussions of immersion and realism. In Game Sound, Karen Collins draws on a range of sources-including composers, sound designers, voice-over actors and other industry professionals, Internet articles, fan sites, industry conferences, magazines, patent documents, and, of course, the games themselves-to offer a broad overview of the history, theory, and production practice of video game audio. Game Sound has two underlying themes: how and why games are different from or similar to film or other linear audiovisual media; and technology and the constraints it has placed on the production of game audio. Collins focuses first on the historical development of game audio, from penny arcades through the rise of home games and the recent rapid developments in the industry. She then examines the production process for a contemporary game at a large game company, discussing the roles of composers, sound designers, voice talent, and audio programmers; considers the growing presence of licensed intellectual property (particularly popular music and films) in games; and explores the function of audio in games in theoretical terms. Finally, she discusses the difficulties posed by nonlinearity and interactivity for the composer of game music.

Text-to-Speech Synthesis provides a complete, end-to-end account of the process of generating speech by computer. Giving an in-depth explanation of all aspects of current speech synthesis technology, it assumes no specialized prior knowledge. Introductory chapters on linguistics, phonetics, signal processing and speech signals lay the foundation, with subsequent material explaining how this knowledge is put to use in building practical systems that generate speech. Including coverage of the very latest techniques such as unit selection, hidden Markov model synthesis, and statistical text analysis, explanations of the more traditional techniques such as format synthesis and synthesis by rule are also provided. Weaving together the various strands of this multidisciplinary field, the book is designed for graduate students in electrical engineering, computer science, and linguistics. It is also an ideal reference for practitioners in the fields of human communication interaction and telephony.