Forgetting Exceptions is Harmful in Language Learning
Machine Learning - Special issue on natural language learning
Meta-Learning for Phonemic Annotation of Corpora
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
A multistrategy approach to improving pronunciation by analogy
Computational Linguistics
Error bounds for convolutional codes and an asymptotically optimum decoding algorithm
IEEE Transactions on Information Theory
Collecting and evaluating speech recognition corpora for nine Southern Bantu languages
AfLaT '09 Proceedings of the First Workshop on Language Technologies for African Languages
Learning rules and categorization networks for language standardization
EUCCL '10 Proceedings of the NAACL HLT Workshop on Extracting and Using Constructions in Computational Linguistics
Weakly supervised morphology learning for agglutinating languages using small training sets
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
Collecting and evaluating speech recognition corpora for 11 South African languages
Language Resources and Evaluation
Optimizing phonetic encoding for viennese unit selection speech synthesis
COST'09 Proceedings of the Second international conference on Development of Multimodal Interfaces: active Listening and Synchrony
A smartphone-based ASR data collection tool for under-resourced languages
Speech Communication
Hi-index | 0.00 |
The Default&Refine algorithm is a new rule-based learning algorithm that was developed as an accurate and efficient pronunciation prediction mechanism for speech processing systems. The algorithm exhibits a number of attractive properties including rapid generalisation from small training sets, good asymptotic accuracy, robustness to noise in the training data, and the production of compact rule sets. We describe the Default&Refine algorithm in detail and demonstrate its performance on two benchmarked pronunciation databases (the English OALD and Flemish FONILEX pronunciation dictionaries) as well as a newly-developed Afrikaans pronunciation dictionary. We find that the algorithm learns more efficiently (achieves higher accuracy on smaller data sets) than any of the alternative pronunciation prediction algorithms considered. In addition, we demonstrate the ability of the algorithm to generate an arbitrarily small rule set in such a way that the trade-off between rule set size and accuracy is well controlled. A conceptual comparison with alternative algorithms (including Dynamically Expanding Context, Transformation-Based Learning and Pronunciation by Analogy) clarifies the competitive performance obtained with Default&Refine.