Our research addresses both basic and applied research in speech and language processing. Our applied research includes significant efforts in biomedical research areas such as computational biology and the nascent field of neurobehavioral engineering, which encompasses topics as diverse as augmentative and alternative communication (AAC) and the discovery of new behavioral "markers" of neurological disorders such as autism and early-phase Alzheimer's disease.

Current projects include novel text input mechanisms for individuals with severe motor impairments, to enable communication via non-invasive brain-computer interfaces; measurement of prosodic anomalies in autism using new prosodic modeling methods; and detection of pathological cognitive change in aging using "markers" dervived via natural language processing (NLP).

While we continue to work in more traditional application areas for our technologies, graduate students in CSLU will have a unique opportunity to work on technologies used to improve the quality of life of impaired populations, while also (and often at the same time) addressing fundamental basic level research questions in NLP or speech.

Research Projects

A Computerized Interactive Game for Remediation of Prosody in Children with Autism
Automated Hearing Tests
Automated Measurement of Dialogue Structure in Autism
Automatic detection of atypical patterns in crossmodal affect
Computer-Based Auditory Skill Building Program for Aural (Re)habilitation
Detection of Autism in Infants
Diagnostic Markers for Childhood Apraxia Speech (Apraxia Markers)
Discriminative Syntactic Language Modeling: Automatic Feature Selection and Efficient Annotation
Efficient Hidden Structure Annotation via Structural Multiple-Sequence Alignments
ERP Based Communication Device for Nonverbal Children on the Autism Spectrum
Expressive and Receptive Prosody in Autism (Prosody in Autism)
Expressive Crossmodal Affect Integration in Autism
From Text to Pictures
Hadoop cluster acquisition, deployment and training for speech and language processing
High-Quality Compression, Enhancement, and Personalization of Text-to-Speech Voices
In Your Own Voice: Personal Augmentative and Alternative Communication Voices
Learning Mixed-Initiative Dialogue Strategies
Machine Learning Approaches to Articulatory Inversion (Articulatory Inver.)
Making Dysarthric Speech Intelligible
Measuring Spoken Language Variability in Elderly Individuals
Modeling Coarticulation for Automatic Speech Recognition
Multi-Threaded Dialogues For Real-Time Applications
Novel Computerized Behavioral Assessment Methods for Attention Deficit Hyperactivity Disorder
Objective Methods for Predicting and Optimizing Synthetic Speech Quality (Synth. Speech Qual.)
Perception of Temporal Structure of Speech in Parkinson's Disease (PD)
Processing and Analysis of QCT Prostate Images for Study of Prostate Diseases (QCT)
Prosody Generation for Child Oriented Speech Synthesis (Prosody Generation)
Robust Information Filtering Techniques for Static and Dynamic State (State Estimation)
Semi-Supervised Discriminative Training of Language Models
Small Footprint Speech Synthesis (Small Footprint)
Synthesis and Perception of Speaker Identity
Tools for Automated Assessment of Language
Translational Refinement of Adaptive Communication System for Locked-in Patients
User Adaptation of AAC Device Voices
User Adaptation of AAC Device Voices - Phase II