The Speech Technology Consortium is a new nonprofit organization designed to help foster innovation across the speech industry by providing support for patent and IP issues. The discussion will describe STC’s work on creating a prior art library that can be used to help companies both create patents and protect against litigation. The discussion will also highlight issues in the U.S. patent system and the changes that may help to address them.

The relationship between the VUI designer and the client plays a critical role in determining whether or not a speech application is successful. Misunderstandings may lead to expensive rewrites and strained relationships, but good communication can lead to win-win solutions. Join us for a frank discussion of the potential roadblocks that can hamper effective vendorclient communication, share stories of your experiences, and brainstorm solutions for building positive and productive relationships.

Graphical User Interfaces frequently use common widgets such as pulldown menus and form fill-in boxes. Users familiar with these widgets can quickly learn to use other applications that contain the same widgets. What are candidate common widgets for voice applications and can they be used across multiple applications on various platforms? What are the pros and cons of standardized voice widgets?

Avatars are realistic representations of humans that gesture and speak to users. Avatars are beginning to appear in speech applications that present information such as newscasts and email readers or guide users to perform complex instructions. Are applications enhanced by these eye-catching avatars? Or, do avatars distract users and take up screen real estate? Listen to the various viewpoints, both pro and con, on this interesting and provocative concept, and add your own opinion and experience.

In this session, we’ll continue last year’s discussion on the desirability and challenges of speech user interfaces in the car. Join us for a discussion on what we’ve learned, obstacles to user adoption, and the impact of recent media and legislative attention to the issue of distracted driving. We’ll continue our discussion on core automotive design principles with respect to prompting, balancing multiple modalities, and the impact of form factor (cell phone versus in-car solutions).

Did you ever wonder why alphanumeric recognition is so hard? Ever wonder why callers say “yes” when you ask if they want A or B? And why do text-to-speech engines mangle all of our names? The field of linguistics hold the answers to these and many other perplexing questions in voice interaction. Bring your questions and chat with two card-carrying linguists for an informal discussion of the role of linguistics in speech technology.

Join us for an informative discussion with a patent attorney on obtaining, maintaining, enforcing, and monetizing patents in the speech industry. We will discuss handling claims of patent infringement, the value of patents, and how patents can make your business more successful.

Speech technologies are widely used in call centers, telephone answering/routing systems, and, more recently, mobile devices. Where does speech go from here? Will speech be used in automated agents that guide users to debug and repair products, to help users navigate the complexity of new functions on hand-held devices, to command and control  household appliances? This out-of-the-box brainstorming session will try to identify new opportunities for speech technologies.

In much of the developing world, access to the internet via personal computers remains quite low, while mobile phone use is widespread. Unlike developed countries, in which individuals rely on the personal computers for access to information and self-service transactions, in the developing world, mobile phones are the primary means of communication and data access. Join us for a discussion of how speech technologies on mobile phones can be used to improve the lives of millions of people in developing countries.

Recent legislation in several states and municipalities around the country require drivers to use hands-free kits to use their mobile phones and have banned texting while driving. A newly developed application allows drivers to send and receive text messages using a speech-only interface, which makes the interaction similar to a hands-free phone call. Join us as we discuss the implications of voice texting and whether it sufficiently reduces the safety hazards associated with texting.

Automated agents and human agents have their advantages and disadvantages in the call center. Can these two agents be merged? For example, can a human agent monitor automated agents, stepping in when the automated agent fails? Can users switch back and forth between human and automated agents? Is the data entered into automated agents secure if the automated agent is monitored by a human agent? What will the future of combined human/automated agents be?

What are the benefits and disadvantages of migrating voice-only IVR applications to multimodal applications on mobile devices? How can voice-only applications take advantage of the small screen on many mobile devices? What changes to a voice-only application’s structure are necessary? Must the application be entirely redesigned and re-implemented?