2002 · 29 citations · 7 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingLanguage ModelingLanguage ModelsPattern RecognitionSpeech RecognitionSpoken CorporaTopic ModelingSpeech Pattern RecognitionSpeech Recognition AccuracySpeech Recognition EvaluationTelephone Speech AnalysisTopic ClassificationTopic LabelingWord Error Rate
We revisit a topic identification test on the Switchboard Corpus first reported by Gillick et al. (see Proc. ICASSP-93, 1993 and ARPA Workshop on Human Language Technology, 1993). This approach to topic ID uses a large vocabulary continuous speech recognizer as a front-end to transcribe the speech and then scores the transcripts using a set of topic-specific language models. Our recognition of conversational telephone speech has improved dramatically in the three years since the original test, dropping from word error rates in the 90%'s to those in the 40%'s. Changing only the recognition engine but otherwise leaving our 1993 topic ID system in place, the resulting rate of message misclassification drops from 33/120 in 1993 down to 1/120 now-the same error rate that we obtain from the true transcriptions. This paper describes the topic classification test and the many improvements to the recognition engine that made such a dramatic reduction possible.
7
Speaker normalization on conversational telephone speech
Steven Wegmann, Don McAllaster, Jeremy Orloff et al. · 2002 · 173 citations
Larry Gillick, James Baker, James Baker et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 1993 · 36 citations
Automatic language identification using large vocabulary continuous speech recognition
Sonia Mendoza, Larry Gillick, Steve Lowe et al. · 2002 · 28 citations
Computing, Computer Science, Spanish +12