Multimodal Interactive Systems Management

This book provides a synthesis of the multifaceted field of interactive multimodal information management. The subjects treated include spoken language processing, image and video processing, document and handwriting analysis, identity information and interfaces. The book concludes with an overview of the highlights of the progress of the field during the past ten years, as well as the problems that are now under investigation and that offer the most promising results for the future. The book is addressed to the graduate student/postdoc level, but much of the book will be accessible to all those with a general background in information processing.

"This book provides concepts, methodologies, and applications used to design and develop multimodal systems"--Provided by publisher.

Adaptive Multimodal Interactive Systems introduces a general framework for adapting multimodal interactive systems and comprises a detailed discussion of each of the steps required for adaptation. This book also investigates how interactive systems may be improved in terms of usability and user friendliness while describing the exhaustive user tests employed to evaluate the presented approaches. After introducing general theory, a generic approach for user modeling in interactive systems is presented, ranging from an observation of basic events to a description of higher-level user behavior. Adaptations are presented as a set of patterns similar to those known from software or usability engineering.These patterns describe recurring problems and present proven solutions. The authors include a discussion on when and how to employ patterns and provide guidance to the system designer who wants to add adaptivity to interactive systems. In addition to these patterns, the book introduces an adaptation framework, which exhibits an abstraction layer using Semantic Web technology.Adaptations are implemented on top of this abstraction layer by creating a semantic representation of the adaptation patterns. The patterns cover both graphical interfaces as well as speech-based and multimodal interactive systems.

This book systematically addresses the quantification of quality aspects of multimodal interactive systems. The conceptual structure is based on a schematic view on human-computer interaction where the user interacts with the system and perceives it via input and output interfaces. Thus, aspects of multimodal interaction are analyzed first, followed by a discussion of the evaluation of output and input and concluding with a view on the evaluation of a complete system.

In the past twenty years, computers and networks have gained a prominent role in supporting human communications. This book presents recent research in multimodal information processing, which demonstrates that computers can achieve more than what telephone calls or videoconferencing can do. The book offers a snapshot of current capabilities for the analysis of human communications in several modalities – audio, speech, language, images, video, and documents – and for accessing this information interactively. The book has a clear application goal, which is the capture, automatic analysis, storage, and retrieval of multimodal signals from human interaction in meetings. This goal provides a controlled experimental framework and helps generating shared data, which is required for methods based on machine learning. This goal has shaped the vision of the contributors to the book and of many other researchers cited in it. It has also received significant long-term support through a series of projects, including the Swiss National Center of Competence in Research (NCCR) in Interactive Multimodal Information Management (IM2), to which the contributors to the book have been connected.

This book contains the outcome of the 9th IFIP WG 5.5 International Summer Workshop on Multimodal Interfaces, eNTERFACE 2013, held in Lisbon, Portugal, in July/August 2013. The 9 papers included in this book represent the results of a 4-week workshop, where senior and junior researchers worked together on projects tackling new trends in human-machine interaction (HMI). The papers are organized in two topical sections. The first one presents different proposals focused on some fundamental issues regarding multimodal interactions, i.e., telepresence, speech synthesis and interactive modeling. The second is a set of development examples in key areas of HMI applications, i.e., education, entertainment and assistive technologies.

This preface tells the story of how Multimodal Usability responds to a special challenge. Chapter 1 describes the goals and structure of this book. The idea of describing how to make multimodal computer systems usable arose in the European Network of Excellence SIMILAR – “Taskforce for cre- ing human-machine interfaces SIMILAR to human-human communication”, 2003– 2007, www. similar. cc. SIMILAR brought together people from multimodal signal processing and usability with the aim of creating enabling technologies for new kinds of multimodal systems and demonstrating results in research prototypes. Most of our colleagues in the network were, in fact, busy extracting features and guring out how to demonstrate progress in working interactive systems, while claiming not to have too much of a notion of usability in system development and evaluation. It was proposed that the authors support the usability of the many multimodal pro- types underway by researching and presenting a methodology for building usable multimodal systems. We accepted the challenge, rst and foremost, no doubt, because the formidable team spirit in SIMILAR could make people accept outrageous things. Second, h- ing worked for nearly two decades on making multimodal systems usable, we were curious – curious at the opportunity to try to understand what happens to traditional usability work, that is, work in human–computer interaction centred around tra- tional graphical user interfaces (GUIs), when systems become as multimodal and as advanced in other ways as those we build in research today.

The Graphical User Interface (GUI), as the most prevailing type of User Interface (UI) in today's interactive applications, restricts the interaction with a computer to the visual modality and is therefore not suited for some users (e.g., with limited literacy or typing skills), in some circumstances (e.g., while moving around, with their hands or eyes busy) or when the environment is constrained (e.g., the keyboard and the mouse are not available). In order to go beyond the GUI constraints, the Multimodal (MM) UIs apear as paradigm that provide users with great expressive power, naturalness and flexibility. In this thesis we argue that developing MM UIs combining graphical and vocal modalities is an activity that could benefit from the application of a methodology which is composed of: a set of models, a method manipulating these models and the tools implementing the method. Therefore, we define a design space-based method that is supported by model-to-model colored transformations in order to obtain MM UIs of information systems. The design space is composed of explicitly defined design options that clarify the development process in a structured way in order to require less design effort. The feasability of the methodology is demonstrated through three case studies with different levels of complexity and coverage. In addition, an empirical study is conducted with end-users in order to measure the relative usability level provided by different design decisions.