This document outlines a system for labeling self-repairs in spontaneous speech. The system marks the location and extent of a repair, as well as relevant words in the region of the repair. Together these labels determine the relationship between the "error" and the hypothesized "correction." The system is designed to be able to capture distinctions among different repair patterns while remaining easy to learn, apply, and integrate into existing transcription ...
The authors have analyzed 607 sentences of spontaneous human-computer speech data containing repairs that were drawn from a total corpus of 10,718 sentences. In this paper, they present criteria and techniques for automatically detecting the presence of a repair, its location, and making the appropriate correction. The criteria involve integration of knowledge from several sources: pattern matching, syntactic and semantic analysis, and acoustics. In summary, disfluencies occur at high enough ...
Reports by Author
