a;d

Enriching speech recognition output with sentence boundaries improves its human readability and enables further processing by downstream language processing mod-ules. We have constructed an HMM system to detect sentence boundaries that uses both the prosodic and textual information. In this system, the sentence boundaries are detected by building a classier in which at each interword boundary, a decision is made as to whether or not it ends a sentence. Since there are more nonsentence boundaries than sentence boundaries in the data, the prosody model, which is im-plemented as a decision tree classier, must be constructed to eectively learn from the imbalanced data distribution. To address this problem, we investigate a variety of sampling approaches and a bagging scheme. A pilot study was carried out to select methods to apply to the full NIST sentence boundary evaluation task across two corpora, using both the reference transcription and the recognition output. In the pilot study, we found that when classication error rate is a performance measure, using the original training set achieves the best performance among th