A Baseline For The Transcription Of Italian Broadcast News
| Venue: | IN PROC. OF ICASSP |
| Citations: | 4 - 3 self |
BibTeX
@INPROCEEDINGS{Brugnara_abaseline,
author = {F. Brugnara and M. Cettolo and M. Federico and D. Giuliani},
title = {A Baseline For The Transcription Of Italian Broadcast News},
booktitle = {IN PROC. OF ICASSP},
year = {},
publisher = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper presents the first achievements in the development of a broadcast news transcription system to be applied for the processing of huge audio archives. In particular, the Italian broadcast news corpus under collection is introduced, and the first implemented baseline system is outlined. The baseline system consists of an audio segmentation module and a speech recognizer featuring a recursive Viterbi beam search, a 64K-word lexicon, a treebased trigram LM representation, and MLLR adaptation. The word error rate of the baseline was 20.9% on planned studio speech and 28.8% on the whole test set.
Citations
| 275 | Maximum likelihood linear transformations for HMMbased speech recognition - Gales - 1998 |
| 149 | On structuring probabilistic dependencies in stochastic language modeling. Computer Speech and Language - Ney, Essen, et al. - 1994 |
| 40 | environment and channel change detection and clustering via the bayesian information criterion - Speaker - 1998 |
| 24 | Dynamic language models for interactive speech applications - Brugnara, Federico - 1997 |
| 19 | Improvements in Beam Search - Steinbiss, Tran, et al. - 1994 |
| 14 | Improvements in tree-based language model representation - Brugnara, Cettolo - 1995 |
| 7 | Language Model Estimations and Representations for Real-Time Continuous Speech Recognition - Antoniol, Brugnara, et al. - 1995 |
