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 theoretical framework which formulates the two tasks as complementary 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. |
Year | DOI | Venue |
---|---|---|
1993 | 10.3115/1075671.1075697 | HLT |
Keywords | Field | DocType |
novel approach,switchboard corpus,telephone conversation,speaker identification,theoretical framework,complementary problem,message identification system,large vocabulary continuous speech | Speaker identification,Computer science,Speech recognition,Speaker recognition,Artificial intelligence,Speaker diarisation,Natural language processing,Vocabulary | Conference |
ISBN | Citations | PageRank |
1-55860-324-7 | 12 | 4.13 |
References | Authors | |
7 | 11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Barbara Peskin | 1 | 68 | 25.14 |
Larry Gillick | 2 | 89 | 32.78 |
Yoshiko Ito | 3 | 47 | 18.65 |
Stephen Lowe | 4 | 26 | 11.16 |
Robert Roth | 5 | 46 | 27.12 |
Francesco Scattone | 6 | 65 | 15.63 |
James Baker | 7 | 66 | 15.44 |
Janet Baker | 8 | 29 | 13.90 |
John Bridle | 9 | 12 | 4.13 |
Melvyn J. Hunt | 10 | 60 | 14.38 |
Jeremy Orloff | 11 | 17 | 6.99 |