This paper focuses on an approach to improve automatic phonetic transcription of proper nouns. The method is based on a two-level iterative process that extract the phonetic variants from the audio signals before filtering the irrelevant variants. The evaluation of the method shows a decreasing of the Word Error Rate (WER) on segments of speech with proper nouns, without affecting negatively the WER on the rest of the corpus (ESTER corpus of French broadcast news).
Cite as: Laurent, A., Meignier, S., Merlin, T., Deléglise, P. (2010) Acoustics-based phonetic transcription method for proper nouns. Proc. Interspeech 2010, 2286-2289, doi: 10.21437/Interspeech.2010-627
@inproceedings{laurent10_interspeech, author={Antoine Laurent and Sylvain Meignier and Teva Merlin and Paul Deléglise}, title={{Acoustics-based phonetic transcription method for proper nouns}}, year=2010, booktitle={Proc. Interspeech 2010}, pages={2286--2289}, doi={10.21437/Interspeech.2010-627} }