Speech & natural language publications

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.

We present a maximum entropy language model that incorporates both syntax and semantics via a dependency grammar.

This paper describes our work in developing multilingual (Swedish and English) speech recognition systems in the ATIS domain. The acoustic component of the multilingual systems is realized through sharing Gaussian…

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…

This paper studies the effects of handset distortion on telephone-based speaker recognition performance. Results on the 1996 NIST Speaker Recognition Evaluation corpus show that using handset-matched background models reduces false…

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…

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…

This paper presents a speech-enabled WWW demonstration based on the Air Travel Information System (ATIS) domain. SRI’s speech recognition technology and natural language understanding are fully integrated in a Java…

We describe the development of the SRI system evaluated in the 1996 DARPA continuous speech recognition (CSR) Hub4 partitioned evaluation (PE). The task for the Hub4 evaluation was to recognition…

In SRI's language modeling experiments for the Hub4 domain, three basic approaches were pursued: interpolating multiple models estimated from Hub4 and non-Hub4 training data, adapting the language model (LM) to…

This paper describes a prototype application which combines speaker identification technology and an agent architecture to provide user-definable monitors for incoming voicemail messages. Through a Web-distributable Java user interface, the…

We ask whether lexical hesitations in spontaneous speech tend to precede words that are difficult to predict. We define predictability in terms of both transition probability and entropy, in the…