A system for the segmentation and transcription of Italian Audio News

This paper presents the development of an Italian broadcast news transcription system, to be applied for the indexing of multimedia archives. Moreover, a broadcast news corpus under collection at ITC-irst is introduced. The system processes the input audio stream in four stages. The first one performs audio segmentation via the Bayesian Information Criterion (BIC) and classification by Gaussians mixtures modeling. The second stage groups spectrally homogeneous speech segments, again using the BIC method, in order to provide speaker clusters suitable for the following adaptation module. The third stage adapts the acoustic models to each selected cluster and, finally, the fourth stage transcribes the audio data employing cluster adapted models. The achieved word error rate, measured on a 1h:15m test set, corresponding to 6 news programs, was 21.5%.