An experimental offline investigation of the performance of connected digits recognition was performed on children in the age range four to eight years. Poor performance using adult models was improved significantly by adaptation and vocal tract length normalisation but not to the same level as training on children. Age dependent models were tried with limited advantage. A combined adult and child training corpus maintained the performance for the separately trained categories. Linear frequency compression for vocal tract length normalization was attempted but estimation of the warping factor was sensitive to non-speech segments and background noise. Phoneme-based word modeling outperformed the whole word models, even though the vocabulary only consisted of digits.
Cite as: Elenius, D., Blomberg, M. (2005) Adaptation and normalization experiments in speech recognition for 4 to 8 year old children. Proc. Interspeech 2005, 2749-2752, doi: 10.21437/Interspeech.2005-702
@inproceedings{elenius05_interspeech,
author={Daniel Elenius and Mats Blomberg},
title={{Adaptation and normalization experiments in speech recognition for 4 to 8 year old children}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={2749--2752},
doi={10.21437/Interspeech.2005-702}
}