News, and ABC World News Tonight. The data will be of (2007)
Larry Gillick, Yoshiko Ito, Linda Manganaro, Michael Newman, Francesco Scattone, Steven Wegmann, ...
Dragon Systems has agreed to provide automatically generated transcripts for around 1000 hours of Broadcast News, annotated with word-level time-markings and confidence estimates. Pilot transcripts...
RECOGNIZING CALL-CENTER SPEECH USING MODELS TRAINED FROM OTHER DOMAINS (2007)
Erica Bernstein, Don Mcallaster, Larry Gillick, Barbara Peskin
In this paper, we introduce a new conversational speech task--recognizing call-center speech-- using data collected from Dragon's own technical support line. We compare performance of models...
RECOGNIZING CALL-CENTER SPEECH USING MODELS TRAINED FROM OTHER DOMAINS (2007)
Erica Bernstein, Don Mcallaster, Larry Gillick, Barbara Peskin
In this paper, we introduce a new conversational speech task – recognizing call-center speech – using data collected from Dragon’s own technical support line. We compare performance of models...
Rapid Match Training for Large Vocabularies (2007)
Gillick, Larry, Peskin, Barbara, Roth, Robert
This paper describes a new algorithm for building rapid match models for use in Dragon's continuous speech recognizer. Rather than working from a single representative token for each word, the new...
Large Vocabulary Recognition of Wall Street Journal Sentences at Dragon Systems (2007)
Baker, James, Baker, Janet, Bamberg, Paul, Bishop, Kathleen, Gillick, Larry, Helman, Vera, ...
In this paper we present some of the algorithm improvements that have been made to Dragon's continuous speech recognition and training programs, improvements that have more than halved our error rate...
Dragon Systems Resource Management Benchmark Results -February 1991 (2007)
Baker, James, Baker, Janet, Bamberg, Paul, Gillick, Larry, Lamel, Lori, Roth, Robert, ...
In this paper, we present preliminary results obtained at Dragon Systems on the Resource Management benchmark task. The basic conceptual units of our system are Phonemes-in-context (PICs), which are...
Dragon systems' 1998 broadcast news transcription system for Mandarin (1999)
Steven Wegmann, Puming Zhan, Ira Carp, Michael Newman, Jon Yamron, Larry Gillick
In this paper we shall describe key improvements to Dragon’s Broadcast News Transcription System, which include: the addition of a speaker-change detection algorithm to our preprocessing subsystem,...
Dragon systems' 1998 broadcast news transcription system for Mandarin (1999)
Steven Wegmann, Puming Zhan, Ira Carp, Michael Newman, Jon Yamron, Larry Gillick
In this paper we shall describe key improvements to Dragon's Broadcast News Transcription System, which include: the addition of a speaker-change detection algorithm to our preprocessing...
Studies with fabricated Switchboard data: exploring sources of model-data mismatch (1998)
Don Mcallaster, Larry Gillick, Francesco Scattone, Mike Newman
We present a study of data simulated using acoustic models trained on Switchboard data, and then recognized using various Switchboard-trained acoustic models. The Switchboard-trained models yield...
Dragon System’s 1997 broadcast news transcription system (1998)
Steven Wegmann, Francesco Scattone, Ira Carp, Larry Gillick, Robert Roth, Jon Yamron
This system represents Dragon's first participation in the HUB4 evaluations since the 1995 Marketplace dry run. At that time, we used a fairly complicated system which had three sets
Studies With Fabricated Switchboard Data: Exploring Sources Of Model-Data Mismatch (1998)
Don Mcallaster Larry, Larry Gillick, Francesco Scattone, Mike Newman
We present a study of data simulated using acoustic models trained on Switchboard data, and then recognized using various Switchboard-trained acoustic models. The Switchboard-trained models yield...
Automatic language identification using large vocabulary continuous speech recognition (1996)
Sergio Mendoza, Larry Gillick, Yoshiko Ito, Stephen Lowe, Michael Newinan
We have developed a highly accurate automatic lan-guage identification system based on large vocabulary continuous speech recognition (LVCSR). Each test utterance is recognized in a number of...
Speaker Verification through Large Vocabulary Continuous Speech Recognition (1996)
Michael Newman, Larry Gillick, Yoshiko Ito, Don Mcallaster, Barbara Peskin
We present a study of a speaker verification system for telephone data based on large-vocabulary speech recognition. After describing the recognition engine, we give details of the verification...
Steve Lowe, Anne Demedts, Larry Gillick, Mark M, Barbara Peskin
The goal of this study is to evaluate the potential for using large vocabulary continuous speech recognition as an engine for automatically classifying utterances according to the language being...
Dragon systems resource management benchmark results–February (1991)
James Baker, Janet Baker, Pard Bamberg, Larry Gillick, Lori Lamei, Robert Roth, ...
In this paper we present preliminary results obtained at Dragon Systems on the Resource Maaaagernent benchmark task. The basic conceptual units of our system are Phonemes-m-Context (PICs), which are...