Add to ORKGIn (Ward and Vega 2008) we examined how how word probabilities vary with time into utterance, and proposed a method for using this information to improve a language model. In this report we examine some ancillary issues in the modeling and exploitation of these regularities
Previous studies show that immediate and long range prosodic context provide benecial info...
This thesis contributes to the research domain of statistical language modeling. In this domain, the...
Speech recognition relies on the language model in order to decode an utterance, and in general a be...
Temporal regularities in speech, such as interdependencies in the timing of speech events, are thoug...
In this paper we investigate whether more accurate modeling of differences in language in different ...
The use of language is one of the defining features of human cognition. Focusing here on two key fea...
Time-to-event prediction tasks are common in conversation modelling, for applications such as predic...
Time is frequently conceptualized as a dimension apart from others, binding disparate processes thro...
Statistical language modelling may not only be used to uncover the patterns which underlie the compo...
While theories on predictive processing posit that predictions are based on one’s prior experiences,...
Numerous factors influence speech timing. Statistical analysis can identify an order of importance a...
Natural language is rich and varied, but also highly struc-tured. The rules of grammar are a primary...
This paper introduces a psycholinguistic model of sentence processing which combines a Hidden Markov...
There has been a large body of research on distributional models, which are computational models of ...
Previous studies show that immediate and long range prosodic context provide beneficial information ...
Previous studies show that immediate and long range prosodic context provide benecial info...
This thesis contributes to the research domain of statistical language modeling. In this domain, the...
Speech recognition relies on the language model in order to decode an utterance, and in general a be...
Temporal regularities in speech, such as interdependencies in the timing of speech events, are thoug...
In this paper we investigate whether more accurate modeling of differences in language in different ...
The use of language is one of the defining features of human cognition. Focusing here on two key fea...
Time-to-event prediction tasks are common in conversation modelling, for applications such as predic...
Time is frequently conceptualized as a dimension apart from others, binding disparate processes thro...
Statistical language modelling may not only be used to uncover the patterns which underlie the compo...
While theories on predictive processing posit that predictions are based on one’s prior experiences,...
Numerous factors influence speech timing. Statistical analysis can identify an order of importance a...
Natural language is rich and varied, but also highly struc-tured. The rules of grammar are a primary...
This paper introduces a psycholinguistic model of sentence processing which combines a Hidden Markov...
There has been a large body of research on distributional models, which are computational models of ...
Previous studies show that immediate and long range prosodic context provide beneficial information ...
Previous studies show that immediate and long range prosodic context provide benecial info...
This thesis contributes to the research domain of statistical language modeling. In this domain, the...
Speech recognition relies on the language model in order to decode an utterance, and in general a be...