A
prosody-only decision-tree model for disfluency detection
|
Elizabeth Shriberg, Rebecca Bates, and
Andreas Stolcke
|
|
| Abstract |
| Speech disfluencies (filled pauses, repetitions, repairs, and false
starts) are pervasive in spontaneous speech. The ability to detect and correct
disfluencies automatically is important for effective natural language understanding, as
well as to improve speech models in general. Previous approaches to disfluency detection
have relied heavily on lexical information, which makes them less applicable when word
recognition is unreliable. We have developed a disfluency detection method using decision
tree classifiers that use only local and automatically extracted prosodic features.
Because the model doesn't rely on lexical information, it is widely applicable even when
word recognition is unreliable. The model performed significantly better than chance at
detecting four disfluency types. It also outperformed a language model in the detection of
false starts, given the correct transcripｭtion. Combining the prosody model with a
specialized language model improved accuracy over either model alone for the detection of
false starts. Results suggest that a prosody only model can aid the automatic detection of
disfluencies in spontaneous speech. |
|
|
| Shriberg,
E., R. Bates, & A. Stolcke 1997 A prosody-only decision-tree model for
disfluency detection. In Proceedings of Eurospeech 97, Rhodes, Greece. |
