Publications
-
Automatic Disfluency Identification in Conversational Speech Using Multiple Knowledge Sources
This work investigates a number of knowledge sources for disfluency detection, including acoustic-prosodic features, a language model (LM) to account for repetition patterns, a part-of-speech (POS) based LM, and rule-based…
-
Iterative Statistical Language Model Generation for Use with an Agent-Oriented Natural Language Interface
We describe a method for developing a statistical language model (SLM) with high keyword spotting accuracy for a natural language interface (NLI). The NLI is based on the Adaptive Agent…
-
Unlocking The Learning Value Of Wireless Mobile Devices
At the moment ‘wireless mobile technologies for education’ are incredibly diverse and incompatible; to achieve scale, a strong vision will be needed to lead to standardisation, overcoming the tendency to…
-
Nucleotide sequence based characterizations of two cryptic plasmids from the marine bacterium Ruegeria isolate PR1b
Given the nature of the putative proteins encoded by both plasmids it is possible that these plasmids enhance the metabolic and physiological flexibility of the host bacterium, and thus its…
-
National Early Intervention Longitudinal Study (NEILS): Service Record A
For the study, every six months an early intervention professional completed a questionnaire on received services, including information regarding the transition out of early intervention.
-
National Early Intervention Longitudinal Study (NEILS): Service Record B
An early intervention professional completed a questionnaire on the services provided to each NEILS family, including information regarding the transition out of early intervention. Version A of the service record…
-
The Modified Group Delay Function and Its Application to Phoneme Recognition
Exploring a new spectral representation of speech signals through group delay functions.
-
Prosodic Knowledge Sources for Automatic Speech Recognition
We investigate three models, each exploiting a different level of prosodic information, in rescoring N-best hypotheses according to how well recognized words correspond to prosodic features of the utterance.
-
Novel Approaches to Arabic Speech Recognition: Report from the 2002 Johns Hopkins Summer Workshop
This paper reports on our project at the 2002 Johns Hopkins Summer Workshop, which focused on the recognition of dialectal Arabic.
-
Literature Review Of Instructional Sensitivity And Opportunity To Learn Studies
-
The Robustness of an Almost-Parsing Language Model Given Errorful Training Data
An almost-parsing language model has been developed that provides a framework for tightly integrating multiple knowledge sources. Lexical features and syntactic constraints are integrated into a uniform linguistic structure (called…
-
Training a Prosody-Based Dialog Act Tagger from Unlabeled Data
Here we investigate the use of unlabeled data for training HMM-based dialog act taggers. Three techniques are shown to be effective for bootstrapping a tagger from very small amounts of…