Speech & natural language publications
-
Handling Compound Nouns in a Swedish Speech-Understanding System
This paper describes and evaluates a simple and general solution to the handling of compound nouns in Swedish and other languages in which compounds can be formed by concatenation of…
-
Automatic Linguistic Segmentation of Conversational Speech
We present a simple automatic segmenter of transcripts based on N-gram language modeling. We also study the relevance of several word-level features for segmentation performance. Using only word-level information, we…
-
Disfluencies in Switchboard
Disfluencies are prevalent in spontaneous speech, and are relevant to both human speech communication and speech processing by machine. This paper reports selected results on Switchboard and two comparison corpora…
-
Modeling Pitch Range Variation Within and Across Speakers: Predicting F0 Targets when “Speaking Up”
We study F0 variation produced by "speaking up", as part of a larger study of pitch range variation within and across speakers. We provide a function to predict target F0…
-
Designing for Cognitive Communication: Epistemic Fidelity or Collaborative Inquiry?
This article examines the generalization of the mental model principle to communication of a system of concepts across worldviews.
-
Stressed and Unstressed Pronouns: Complementary Preferences
I present a unified account of interpretation preferences of stressed and unstressed pronouns in discourse. The central intuition is the Complementary Preference Hypothesis that predicts the interpretation preference of a…
-
VILTS: The Voice-Interactive Language Training System
ECHOS is a voice interactive language training system being developed to foster improvement in French comprehension and speaking skills, incorporating speech recognition and pronunciation evaluation.
-
Acoustic Adaptation Using Non-Linear Transformations of HMM Parameters
Speech recognition performance degrades significantly when there is a mismatch between testing and training conditions. Linear transformation-based maximum-likelihood (ML) techniques have been proposed recently to tackle this problem. In this…
-
A Maximum-Likelihood Approach to Stochastic Matching for Robust Speech Recognition
We present a maximum-likelihood(ML)stochastic matching approach to decrease the acoustic mismatch between a test utterance and a given set of speech models so as to reduce the recognition performance degradation…
-
Noise-resistant Feature Extraction and Model Training for Robust Speech Recognition
We present a novel noise-robust feature extraction algorithm that is a combination of our previously developed minimum mean square error (MMSE) log-energy estimation algorithm and the probabilistic optimum filtering (POF)…
-
Statistical Language Modeling for Speech Disfluencies
We introduce a language model that predicts disfluencies probabilistically and uses an edited, fluent context to predict following words. It uses dynamic programming to compute the probability of a word…
-
An Experimental Study of Acoustic Adaptation Algorithms
In this paper we focus on transformation-based maximum-likelihood (ML) adaptation.