Speech input is a natural text entry method for handheld devices that are used in different contexts. We conducted an experiment to understand effects of input (speaking) style (phrasal vs. sentence input) on Chinese text entry rates and user satisfaction with other two variables: recognition rate (50%, 70% and 90%) and message length (10 vs. 20 characters). Wizard of Oz was applied in the expe...

Written documents created through dictation differ significantly from a true verbatim transcript of the recorded speech. This poses an obstacle in automatic dictation systems as speech recognition output needs to undergo a fair amount of editing in order to turn it into a document that complies with the customary standards. We present an approach that attempts to perform this edit from recogniz...

Medicine is a “knowledge-intensive service environment” that requires not only a great deal of knowledge, training and experience, but also focus and concentration for optimal performance, with interruptions in workflow having the potential to contribute to errors [1]. The effects of these interruptions have been linked to errors in both the laboratory [2,3] and clinical settings [4-13], howeve...

Background Genetic impacts on handwriting legibility and speed, especially in early childhood, are not well understood. The present study used a 2D:4D ratio as a biological marker to investigate the associations between genetic factors with quality and speed of handwriting among the elementary school children. Ma...

This paper addresses the problem of speaker characterization in the speaker-dependent speech recognition problem. Speaker Adaptation and Normalization techniques are designed to reduce the mismatch introduced by inter-speaker variability. Yet there is another source of mismatch introduced by intra-speaker variability. Indeed, the speaking style of a speaker depends on the nature of the speech u...

The performance of large vocabulary recognition systems, for instance in a dictation application, typically deteriorates severely when used in a reverberant environment. This can be partially avoided by adding a dereverberation algorithm as a speech signal preprocessing step. The purpose of this paper is to compare the effect of different speech dereverberation algorithms on the performance of ...

This paper examines the susceptibility of a dictation system to various types of mismatches between the training and testing conditions. With these experiments we intend to find the best training configuration for the system and also to evaluate the efficiency of the speaker adaptation algorithm we use. The paper first presents the components of the dictation system, and then describes a set of...

The combination of Maximum Likelihood Linear Regression (MLLR) with Maximum a posteriori (MAP) adaptation has been investigated for both the enrollment of a new speaker as well as for the asymptotic recognition rate after several hours of dictation. We show that a least mean square approach to MLLR is quite e ective in conjunction with phonetically derived regression classes. Results are presen...