An efficient way to learn English grapheme-to-phoneme rules automatically

Authors:
Kari Torkkola
Affiliations:
Institut Dalle Molle D'Intelligence Artificielle Perceptive, Martigny, Switzerland
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Year:
1993

Citing 5
Cited 2

Toward memory-based reasoning

Communications of the ACM - Special issue on parallelism
A Default Hierarchy for Pronouncing English

IEEE Transactions on Pattern Analysis and Machine Intelligence
A combination of neural network and low-level AI-techniques to transcribe speech into phonemes

COGNITIVA 90 Proceedings of the third COGNITIVA symposium on At the crossroads of artificial intelligence, cognitive science, and neuroscience
An experimental comparison of symbolic and connectionist learning algorithms

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Error-correcting output codes: a general method for improving multiclass inductive learning programs

AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 2

Text independent methods for speech segmentation

Nonlinear Speech Modeling and Applications
Direct posterior confidence for out-of-vocabulary spoken term detection

ACM Transactions on Information Systems (TOIS)

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an efficient way to learn automatically grapheme-to-phoneme mapping rules for English by using Kohonen's concept of Dynamically Expanding Context. This method constructs rules that are most general in the sense of an explicitly defined specificity hierarchy. As the hierarchy, we have used the amount of expanding context around the symbol to be transformed, weighted towards the right. To apply this concept to English text-to-speech mapping, we have used the 20008-word corpus provided in the public domain by Sejnowski and Rosenberg, that was also used in the NETTALK-experiments. Phoneme-level mapping accuracies of 91 per cent with data not used in training demonstrate that the Dynamically Expanding Context is able to capture quite efficiently the context dependent relationships in the corpus.