We propose a novel algorithm to detect disfluency in speech by reformulating the problem as phrase-level statistical machine translation using weighted finite state transducers. We approach the task as translation of noisy speech to clean speech. We simplify our translation framework such that it does not require fertility and alignment models. We tested our model on the Switchboard disfluency-annotated corpus. Using an optimized decoder that is developed for phrase-based translation at IBM, we are able to detect repeats, repairs and filled pauses for more than a thousand sentences in less than a second with encouraging results. Index Terms: disfluency detection, machine translation, speechto-speech translation.
展开▼
