SSLI Lab Projects

Current Projects:

• ITR: Translation Technology for Language Modeling
• EARS Rich Transcription
• Novel Approaches to Acoustic Modeling for Speech Recognition
• Mapping meetings: Language technology to make sense of human interaction
• Automatic Summarization of Recorded Lectures
• Automatic Speech Recognition as a Model for Human Speech Perception
• Information access to spoken documents
• Low-power speech recognition
• Noise Robust ASR
• Graphical Models for ASR
• Discriminative Methods in ASR

Recent Previous Projects:

• Robust Recognition and Dialog Tracking: DARPA Communicator
• Speech Generation for Human-Computer Interaction
• Feature-based automatic language identification
• Training Statistical Language Models with Out-of-Domain Data
• Modeling Structure in Speech above the Segment for Spontaneous Speech Recognition
• Joint Lexicon and Acoustic Model Design for Spontaneous Speech Recognition
• Channel and Noise Compensation for Recognition of Telephone Speech
• High Order Modeling Techniques for Continuous Speech Recognition
• The Boston University Radio News Corpus
• Computational Modeling of Intonation
• Evaluating the Use of Prosodic Information in Speech Recognition and Understanding
• Other Previous Sponsored Research