Daniel C. Burnett

Learn More
We are exploring ways in which to rapidly adapt our neural network classiiers to new speakers and conditions using very small amounts of speech, say, one or a few words. Our approach is to perform a speaker-dependent warping of the frequency scale by selecting a Bark ooset for each speaker. We choose the ooset for a speaker to be the one that maximizes our(More)
This paper describes a study conducted to determine the feasibility of using a spoken questionnaire to collect information for the Year 2000 Census in the USA. To reene the dialogue and to train recognizers, we collected complete protocols from over 4000 callers. For the responses labeled (about half), over 99 percent of the answers contain the desired(More)
This paper reports the results of the development, deployment and testing of a large spoken-language dialogue application for use by the general public. We built an automated spoken questionnaire for the U.S. Bureau of the Census. In the project's rst phase, the basic recognizers and dialogue system were developed using 4,000 calls. In the second phase, the(More)
This paper describes eight telephone-speech corpora at various stages of development at the Center for Spoken Language Understanding. For each corpus, we describe data collection procedures, methods of soliciting callers, protocol used to collect the data, transcriptions that accompany the speech data, and the expected release date. The corpora are(More)
  • 1