Projects

·      DialRC and DialPort

o  a Center that is at the service of the Spoken Dialog community, providing data, running studies, educating and running a Spoken Dialog Challenge http://dialrc.org/ www.skylar.cs.cmu.edu

·      Let’s Go

o  a project using a spoken dialogue system to expand access to such systems to the elderly and to non-native speakers. http://www.speech.cs.cmu.edu/letsgo/

·      Automatic detection of driver distraction

o  using multimodal information, finding times when the driver will be/is distracted and notifying the user in order to prevent accidents

·      LexE

o  a project on lexical entrainment on both sides of the dialog with spoken dialog systems, sometimes with non-native speakers.

·      Crowdsourcing

o  the use of crowdsourcing to render datasets usable and correct. How to respect crowdworkers, paying them correctly,

·      REAP

o  a project to retrieve appropriate, individuated texts for students learning to read, which exists in French and Portuguese as well as in English.

·      Fluency

o  a project to use automatic speech recognition to detect pronunciation errors and to provide appropriate correction information – contact me directly for more information.

·      DialPort

o  NSF-funded DialPort has 3 thrusts: Tools, Portal and Real Challenge. The Portal gives your connected dialog system a stream of user data. You can also request data that other systems have gathered. There is also a list of tools that are available to help you and your students build applications.

·      Let's Go

o  Let’s Go! is building a spoken dialog system that can be used by the general public. The system we are developing for Let’s Go! is designed to work with a much wider population, including groups that typically have trouble interacting with dialog systems, such as non-native English speakers and the elderly.

·      Automatic detection of driver distraction

o  Distracted Driving continues to be a cause of traffic accidents despite prevailing legislation. The goal of this project is to automatically determine when the driver is becoming distracted. This information can be sent to a warning system in a car or can be used to help shut down the distracting activity.

·      LexE

o  a project on lexical entrainment on both sides of the dialog with spoken dialog systems, sometimes with non-native speakers.

·      Crowdsourcing

o  Crowdsourcing has solved the issue of finding users, but it presents new challenges such as how to use a crowdsourcing platform and what type of test is appropriate. DialCrowd makes system assessment using crowdsourcing easier by providing tools, templates and analytics.

·      REAP

o  A project to retrieve appropriate, individuated texts for students learning to read which exists in French and Portuguese as well as in English.

·      FLUENCY

o  Learning a foreign language is not only a question of getting the words and syntax right. You can’t be understood until you can pronounce it well! FLUENCY is designed to let you speak, then give you feedback as to how you did – what to correct, and how to correct it. Using state-of-the-art speech recognition technology, SPHINX from Carnegie Mellon, this interactive software allows you to speak, to get corrections, to listen to yourself and a native speaker and try again, over and over, as many times as you want. FLUENCY is patient and can be customized to do what you want. Practice in the privacy of your PC or phone and then speaker to others when you’re ready! FLUENCY detects phonetic and duration errors in speech. IT can be used for English as a second language and can be adapted to other languages. The user can make it easier or harder to succeed. Other user-adaptive options to maximize learning also exist. The software can be used alone or in conjunction with language classes.