Novel-word pronunciation: a cross-language study
Speech Communication - Speech science and technology: a selection from the papers presented at the Fourth International Conference in Speech Science and Technology (SST-92)
A multistrategy approach to improving pronunciation by analogy
Computational Linguistics
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
Joint-sequence models for grapheme-to-phoneme conversion
Speech Communication
New strategies for pronunciation by analogy
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
| Hi-index | 0.00 |
The relationship between written and spoken words is convoluted in languages with a deep orthography such as English and therefore it is difficult to devise explicit rules for generating the pronunciations for unseen words. Pronunciation by analogy (PbA) is a data-driven method of constructing pronunciations for novel words from concatenated segments of known words and their pronunciations. PbA performs relatively well with English and outperforms several other proposed methods. However, the method inherently generates several candidate pronunciations and its performance depends critically on a good scoring function to choose the best one of them.Previous PbA algorithms have used several different scoring heuristics such as the product of the frequencies of the component pronunciations of the segments, or the number of different segmentations that yield the same pronunciation, and different combinations of these methods, to evaluate the candidate pronunciations. In this article, we instead propose to use a probabilistically justified scoring rule. We show that this principled approach alone yields better accuracy than any previously published PbA algorithm. Furthermore, combined with certain ad hoc modifications motivated by earlier algorithms, the performance can in some cases be further increased.