Login



Champion Sponsor



Donors










Best of MobileHCI 2012

Best Papers

  • An investigation into the use of tactile instructions in snowboarding. Daniel Spelmezan
  • MemReflex: Adaptive Flashcards for Mobile Microlearning. Darren Edge, Stephen Fitchett, Michael Whitney, James Landay

Best Demo

  • Tilt Displays: Display Surfaces with Multi-Axis Tilt and Actuation. Jason Alexander, Andrés Lucero, Sriram Subramanian

Demo honorable mention

  • PoI Poi: Point-of-Interest Poi for Multimodal Tethered Whirling. Michael Cohen

Social Media

The official hashtag for MobileHCI2012 is #mobilehci2012 and you can follow us on Twitter or Facebook.



“Said So! – Speech Application Interaction Design”

Organizers

  • Nitendra Rajput, IBM Research, India.
  • Amit A. Nanavati, IBM Research, India.

Structure

Said So! a three hour Speech Application Interaction Design tutorial.

  • Hour 1: Speech Interactions.

We will begin with a brief overview motivating the importance and relevance of speech-based applications (for developing regions and eyes-free interaction needs). We will present several use-cases based on our experience in the field with several pilots of the Spoken Web[1-4].

  • Hour 2: Call-flow Design and Implementation Considerations.

Here, we will talk about what it takes to design a call-flow, how and why the device capabilities matter, and how these have a bearing on the application: The challenges of building speech applications on devices constrained by memory and processing power. At times, therefore, it makes sense to do some server side speech processing as well. We will delve into issues of how to intelligently split the processing between the server and the client to it to suit our needs.

  • Hour 3: Implementation Task.

Here, we will make the attendees implement a small speech application, where the front-end is on a smart client(android, for example) and the back-end is a Spoken Web site, so that they can implement and experience the application and play with it.

Objectives

At the end of the tutorial, the attendees will

  1. have an appreciation for the need of speech applications and the challenges of using them
  2. be able to design call-flows and analyse the constraints; understand the basics of VoiceXML, and
  3. get a head start on implementing so that they can get started on building applications faster.

Bios

  • Nitendra Rajput

Nitendra Rajput is a Senior Researcher with IBM India Research Lab (IRL). He has been working in the field of mobile interactions for more than ten years. He has worked on Audio Visual Speech recognition, speech recognition systems for Indian languages and on dialog systems in the past. Lately he has been focusing on developing mobile interaction technologies for low-literate users. He is working on the Spoken Web -a voice-driven ecosystem parallel to that of the WWW. The Spoken Web is a network of VoiceSites that can be created by end-users (such as farmers, electricians, carpenters) through their cell- phones using voice as the primary medium of interaction. Specifically, he focuses on navigation and search related problems for the Spoken Web. His interests are in mobile interactions, HCI, statistical signal processing, dialog management, speech and image processing.

  • Amit A. Nanavati

Amit A. Nanavati, another Senior Researcher in the Telecom Solutions Research group at IBM Research – India, is a “Spoken Web” evangelist – trying to promote the vision of a world-wide Spoken Web hosted in the Telecom network, which does not require an Internet connection or the ability to read and write. He also spends time working on Social Network Analysis, as applied to Telecom networks. He is particularly interested in applications of graph theory in various domains and also dabbles with speech in mobile and pervasive environments. Prior to joining IBM, he was with Netscape Communications. He received the BE degree in computer science from the Maharaja Sayajirao University of Baroda and the MS degree and the PhD degree in computer science (distributed computing) from Louisiana State University, Baton Rouge. Before completing his PhD, he spent a summer in the Jet Propulsion Laboratory, California Institute of Technology, NASA. Both Nitendra and Amit have been organizing the “Speech in Mobile and Pervasive Environments” Workshop at MobileHCI since 2006.