This paper presents a Variety IDentification (VID) approach and its application to broadcast news transcription for Portuguese. The phonotactic VID system, based on Phone Recognition and Language Modelling, focuses on a single tokenizer that combines distinctive knowledge about differences between the target varieties. This knowledge is introduced into a Multi-Layer Perceptron phone recognizer by training mono-phone models for two varieties as contrasting phone-like classes. Significant improvements in terms of identification rate were achieved compared to conventional single and fused phonotactic and acoustic systems. The VID system is used to select data to automatically train variety-specific acoustic models for broadcast news transcription. The impact of the selection is analyzed and variety-specific recognition is shown to improve results by up to 13% compared to a standard variety baseline.
Cite as: Koller, O., Abad, A., Trancoso, I., Viana, C. (2010) Exploiting variety-dependent phones in portuguese variety identification applied to broadcast news transcription. Proc. Interspeech 2010, 749-752, doi: 10.21437/Interspeech.2010-276
@inproceedings{koller10_interspeech,
author={Oscar Koller and Alberto Abad and Isabel Trancoso and Céu Viana},
title={{Exploiting variety-dependent phones in portuguese variety identification applied to broadcast news transcription}},
year=2010,
booktitle={Proc. Interspeech 2010},
pages={749--752},
doi={10.21437/Interspeech.2010-276}
}