8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Automatic Disfluency Identification in Conversational Speech Using Multiple Knowledge Sources

Yang Liu (1), Elizabeth Shriberg (2), Andreas Stolcke (2)

(1) International Computer Science Institute, USA
(2) SRI International, USA

Disfluencies occur frequently in spontaneous speech. Detection and correction of disfluencies can make automatic speech recognition transcripts more readable for human readers, and can aid downstream processing by machine. This work investigates a number of knowledge sources for disfluency detection, including acoustic-prosodic features, a language model (LM) to account for repetition patterns, a part-of-speech (POS) based LM, and rule-based knowledge. Different components are designed for different purposes in the system. Results show that detection of disfluency interruption points is best achieved by a combination of prosodic cues, word-based cues, and POS-based cues. The onset of a disfluency to be removed, in contrast, is best found using knowledge-based rules. Finally, specific disfluency types can be aided by the modeling of word patterns.

Full Paper

Bibliographic reference.  Liu, Yang / Shriberg, Elizabeth / Stolcke, Andreas (2003): "Automatic disfluency identification in conversational speech using multiple knowledge sources", In EUROSPEECH-2003, 957-960.