Self-Learning Techniques for Grapheme-to-Phoneme Conversion

In this article, we present a comprehensive review of various experiences with diierent self-learning techniques applied to the task of converting a gra-phemic string into the corresponding phonemic sequence. We also report some experiments carried out both with English words and French proper names. These experiments support the view that taking full advantage of the huge pronunciation dictionaries that we have been developing during the ONOMASTICA project is possible only if the traditional understanding of grapheme-to-phoneme conversion as a classiication problem is questioned.

[1]  Simon M. Lucas,et al.  Syntactic neural networks for bidirectional text-phonetics translation , 1992 .

[2]  Kenneth Ward Church.  Stress assignment in letter‐to‐sound rules for speech synthesis , 1985 .

[3]  Howard C. Nusbaum,et al.  Pronounce : a program for pronunciation by analogy , 1991 .

[4]  Walter Daelemans,et al.  Learnability and markedness in data-driven acquisition of stress , 1993 .

[5]  Wendy G. Lehnert,et al.  Case-based Problem Solving with a Large Knowledge Base of Learned Cases , 1987, AAAI.

[6]  M. Rosson.  The interaction of pronunciation rules and lexical representations in reading aloud , 1985, Memory & cognition.

[7]  George K. Kokkinakis,et al.  Phoneme to grapheme conversion using HMM , 1991, EUROSPEECH.

[8]  David W. Shipman,et al.  Letter‐to‐phoneme rules: A semi‐automatic discovery procedure , 1982 .

[9]  Thomas G. Dietterich,et al.  Error-Correcting Output Codes: A General Method for Improving Multiclass Inductive Learning Programs , 1991, AAAI.

[10]  R. Glushko.  The Organization and Activation of Orthographic Knowledge in Reading Aloud. , 1979 .

[11]  Robert I. Damper,et al.  Speech synthesis by analogy: recent advances and results , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[12]  Kenneth Ward Church,et al.  Morphology and rhyming: two powerful alternatives to letter-to-sound rules for speech synthesis , 1990, SSW.

[13]  William A. Ainsworth,et al.  Connectionist architectures for a text-to-speech system , 1989, EUROSPEECH.

[14]  John A. Bullinaria,et al.  Connectionist Modelling of Spelling , 2019, Proceedings of the Sixteenth Annual Conference of the Cognitive Science Society.

[15]  Andrew R. Golding.  Pronouncing names by a combination of rule-based and case-based reasoning , 1992 .

[16]  Walter Daelemans,et al.  Data-Oriented Methods for Grapheme-to-Phoneme Conversion , 1993, EACL.

[17]  Martin Chodorow,et al.  Using an On-Line Dictionary to Find Rhyming Words and Pronunciations for Unknown Words , 1985, ACL.

[18]  Victor Zue,et al.  Phonological parsing for reversible letter-to-sound/sound-to-letter generation , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[19]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[20]  S. Oakey,et al.  Inductive Learning of Pronunciation Rules by hypothesis Testing and Correction , 1981, IJCAI.

[21]  Paul Dalsgaard,et al.  A Self-learning Approach to Transcription of Proper Names , 1993 .

[22]  Robert I. Damper,et al.  Novel-word pronunciation within a text-to-speech system , 1990, SSW.

[23]  Terrence J. Sejnowski,et al.  Parallel Networks that Learn to Pronounce English Text , 1987, Complex Syst..

[24]  Craig Stanfill.  Memory-based Reasoning Applied to English Pronunciation , 1987, AAAI.

[25]  Mark Bedworth,et al.  NETspeak — A re-implementation of NETtalk , 1987 .

[26]  Raymond J. Mooney,et al.  An Experimental Comparison of Symbolic and Connectionist Learning Algorithms , 1989, IJCAI.

[28]  Robert L. Mercer,et al.  An information theoretic approach to the automatic determination of phonemic baseforms , 1984, ICASSP.

[29]  Kari Torkkola,et al.  A combination of neural network and low-level AI-techniques to transcribe speech into phonemes , 1991 .

[30]  Eugene Charniak,et al.  Statistical language learning , 1997 .

[31]  Robert I. Damper,et al.  Synthesis-by-analogy: A bi-lingual investigation using German and English , 1992 .

[32]  R. A. Sharman,et al.  A bi-directional model of English pronunciation , 1991, EUROSPEECH.

[33]  Thomas G. Dietterich,et al.  A Comparative Study of ID3 and Backpropagation for English Text-to-Speech Mapping , 1990, ML.