Influence of speech recognition errors on topic detection

We investigate the effect of speech-recognition errors on a system for the unsupervised, nearly synchronous clustering of broadcast news stories, using the TDT (Topic Detection and Tracking) Corpora. Two questions are addressed: (1) Are speech recognition errors detrimental to the performance of the system? (2) Can a background collection of contemporaneous clean text improve performance? We investigate both the large-cluster and small-cluster limits.