Publications
-
A Prosody-Only Decision-Tree Model for Disfluency Detection
We have developed a disfluency detection method using decision tree classifiers that use only local and automatically extracted prosodic features. Because the model doesn't rely on lexical information, it is…
-
Diagrammatic Methods for Deriving and Relating Temporal Neural Network Algorithms
We present an alternative approach based on a set of simple block diagram manipulation rules. The approach provides a common framework to derive popular algorithms including backpropagation and backpropagation-through-time, without…
-
A Lognormal Tied Mixture Model of Pitch for Prosody-Based Speaker Recognition
In this work, we develop a statistical model of pitch that allows unbiased estimation of pitch statistics from pitch tracks which are subject to doubling and/or halving.
-
Modeling Linguistic Segment and Turn Boundaries for N-best Rescoring of Spontaneous Speech
We present an N-best rescoring algorithm that removes the effect of segmentation mismatch. Furthermore, we show that explicit language modeling of hidden linguistic segment boundaries is improved by including turn-boundary…
-
Acoustic Clustering and Adaptation for Robust Speech Recognition
We describe an algorithm based on acoustic clustering and acoustic adaptation to significantly improve speech recognition performance. The method is particularly useful when speech from multiple speakers is to be…
-
Explicit Word Error Minimization in N-best List Rescoring
We show that the standard hypothesis scoring paradigm used in maximum-likelihood-based speech recognition systems is not optimal with regard to minimizing the word error rate, the commonly used performance metric…
-
Mixture Input Transformations for Adaptation of Hybrid Connectionist Speech Recognizers
In this paper, we propose a new algorithm to train mixtures of transformation networks (MTNs) in the hybrid connectionist recognition framework. We apply the new algorithm to nonnative speaker adaptation,…
-
Multimodal Interfaces for Internet
In this paper, we present a Java-enabled application with a multimodal (pen and voice) interface over the web. Our implementation approach was to add Java to the set of languages…
-
Using Differential Constraints to Reconstruct Complex Surfaces from Stereo
Stereo reconstruction algorithms often fail to properly deal with complex surfaces, because there is not enough image information. We propose to guide the reconstruction process using a priori information about…
-
Automatic Pronunciation Scoring for Language Instruction
In this paper we show that we can significantly improve HMM- based scores by using average phone segment posterior probabilities. Correlation between machine and human scores went up from r=0.50…
-
Model Transformation for Robust Speaker Recognition from Telephone Data
In the context of automatic speaker recognition, we propose a model transformation technique that renders speaker models more robust to acoustic mismatches and to data scarcity by appropriately increasing their…
-
Neural-Network Based Measures of Confidence for Word Recognition
This paper proposes a probabilstic framework to define and evaluate confidence measures for word recognition. We describe a novel method to combine different knowledge sources and estimate the confidence in…