Designed for attendees new to the speech technology area, this tutorial overviews the speech technologies, user interface design principles, and the markets for this fast-evolving industry. We highlight the key speech technologies, including automatic speech recognition (ASR), text to speech (TTS), voice biometrics, and dialogue management. Learn how these technologies are used to develop interactive voice response (IVR) systems; voice-enabled personal assistants; and voice-enabled mobile applications, assistive applications, and voice applications for use in the car, TV, and other devices/appliances. Learn about the process of developing speech applications, principles, and best practices and the integration of speech with GUI and other UI modalities. Understand the players in the speech technology ecosystem.

Natural language processing (NLP) technology is becoming widely recognized as a key component of conversational systems. More and more speech and multimodal applications are using NLP and NLP resources are becoming increasingly available through web services. Online natural language processing services can supply natural language capabilities to a range of mashups for both speech and text-based applications. This session introduces participants to the possibilities for using natural language processing in their own applications. Following a brief overview, most of the session focuses on interacting with online NLP APIs that perform tasks such as classification, part-of-speech tagging, parsing, and named entity recognition. Attendees can try their hand at supplying their own training data for a simple statistical NLP classifier. For details, see http://www.conversational-technologies.com/ SpeechTEKUniversity.html.

Learn how to develop voice-based apps for Android devices using open source software. Based on a series of step-by- step examples, you learn how to create apps that talk and recognize your speech. Looking first at the basic technologies of text-to-speech and speech recognition, this workshop shows you how to create more complex apps that can perform useful tasks. By the end of the workshop, you know how to develop a simple voice-based personal assistant that you can customize to suit your own needs. This workshop covers 1) an introduction to speech on Android devices and compo- nents of a voice-based personal assistant; 2) text-to-speech synthesis using Google TTS; 3) getting and processing speech recognition results; 4) creating and using libraries for TTS and speech recognition; 5) developing voice-based apps such as a simple conversation assistant; and 6) future trends. Attendees receive a copy of Voice Application Development for Android by Michael F. McTear and Zoraida Callejas.

Testing and quality assurance (QA) are crucial to the success of any speech system, but testing IVR and multimodal systems presents unique challenges. Focusing on multimodal applications that involve speech and other modalities, we describe the multiple layers of testing and QA: engine quality, functional application, VUI, interfaces and infrastructure, load balancing, backup, and recovery. Learn how to do the following: Set the testing goals, targets, and success factors; specify and measure metrics; test and measure "soft" and "immeasurable" targets; test documentation in all stages; and manage a testing project and identify who should be on the testing team.

Google Glass is the first large-scale effort to bring optical wearable computers to the marketplace. It’s unlikely to be the last. Glass is a head-mounted display with many of the features of a smartphone (view screen, audio, microphone and speech recognition, camera, geolocation, touch interfaces) and runs on the Android operating system. Any developer with experience programming web services or smartphone applications need only make a short leap in their user experience sensibilities and learn a few new tools to program Google Glass. We demonstrate the Google Glass user interface and explain how to use the two development kit options—the Mirror API for web service-based development and the GDK (Glass Development Kit), which is a small superset of the standard Android Development Kit. Attendees receive a copy of Redmond’s Programming Google Glass, published by Pragmatic Programmers.

How does one marry speech with a mobile touch interface? What does the speech experience feel like in an app? How to you play to the strengths and weaknesses of each? Natural language input is becoming more and more common in mobile apps especially with the arrival of virtual assistants. Design must continue to focus on the user and adapt the usage of the technology accordingly. The experience needs to be natural, intuitive, intelligent, seamless and provide value. This workshop will look at the integration of technologies as they relate to design, modalities, and associated multimodal design patterns, accompanied by real world examples from mobile apps. The workshop will include exercises that allow participants to explore implications for speech design in a multimodal mobile context.