Word buffering models for improved speech repair parsing
Tim Miller · 2009
This paper describes a time-series model for parsing transcribed speech containing disfluencies. This model differs from previous parsers in its explicit modeling of a buffer of recent words, which allows it to recognize repairs more easily due to the frequent overlap in words between errors and their repairs. The parser implementing this model is evaluated on the standard Switchboard transcribed speech parsing task for overall parsing accuracy and edited word detection.