Our goal is to create technology that makes it possible for everyone in the world to interact with with computers via natural spoken language.

We believe that conversational interfaces will enable us to converse with machines much in the same way that we communicate with one another and will play a fundamental role in facilitating our move toward an information-based society.

We address a broad range of research topics, which are grouped according to three basic questions

  1. Who is talking: this area focuses on paralinguistic issues like speaker verification, language, dialect identification, who spoke when, and health-related issues as they manifest in speech signals.
  2. What is said: this area addresses core speech recognition capabilities and addresses challenges related to noise robustness, limited linguistic resources, and unsupervised language acquisition.
  3. What is meant: this final area focuses more on the boundary between speech and natural language processing, and includes topics related to speech understanding, sentiment analysis and dialogue.

Members

Projects

 11 More

News

 4 More