Topic and Speaker Identification via Large Vocabulary Continuous Speech Recognition

Topic and Speaker Identification via Large Vocabulary Continuous Speech Recognition Barbara Peskin, Larry Gillick, Yoshiko Ito, Stephen Lowe, Robert Roth, Francesco Scattone, James Baker, Janet Baker, John Bridle, Melvyn Hunt, Jeremy Orloff Dragon Systems, Inc. 320 Nevada Street Newton, Massachusetts 02160 ABSTRACT In this paper we exhibit a novel approach to the problems of topic and speaker identification that makes use of a large vocabulary continuous speech recognizer. We present a theo- retical framework which formulates the two tasks as comple- mentary problems, and describe the symmetric way in which we have implemented their solution. Results of trials of the message identification systems using the Switchboard corpus of telephone conversations are reported. 1. INTRODUCTION The task of topic identification is to select from a set of possibilities the topic that is most likely to represent the subject matter covered by a sample of speech. Simi- larly, speaker identification requires selecting from a list of possibilities the speaker most likely to have produced the speech. In this paper, we present a novel approach to the problems of topic and speaker identification which uses a large vocabulary continuous speech recognizer as a preprocessor of the speech messages. The motivation for developing improved message identi- fication systems derives in part from the increasing re- liance on audio databases such as arise from voice mail, for example, and the consequent need to extract informa- tion from them. Technology that is capable of searching such a database of recorded speech and classifying mate- rial by subject matter or by speaker would have substan- tial value, much as text-based information retrieval tech- nology has for textual corpora. Several approaches to the problems of topic and speaker identification have already appeared in the literature. For example, an approach to topic identification using wordspotting is described in [1] and approaches to the speaker identification problem are reported in [2] and [3]. Dragon Systems' approach to the message identification tasks depends crucially on the existence of a large vo- cabulary continuous speech recognition system. We view the tasks of topic and speaker identification as comple- mentary problems: for topic identification, the speaker is irrelevant and only the subject matter is of interest; for speaker identification, the reverse is true. For efficiency of computation, in either case we first use a speaker- independent topic-independent recognizer to transcribe the speech messages. The resulting output is then scored using topic-sensitive or speaker-sensitive models. This approach to the problem of message identification is based on the belief that the contextual information used in a full-scale recognition is invaluable in extract- ing reliable data from difficult speech channels. For ex- ample, unlike standard approaches to topic identifica- tion through spotting a small collection of topic-specific words, the approach via continuous speech recognition should more reliably detect keywords because of the acoustic and language model context available to the recognizer. Moreover, with large vocabulary recognition, the list of keywords is no longer limited to a small set of highly topic-specific (but generally infrequent) words, and …

Content truncated to 500 words