A Finite State and Data-Oriented Method for Grapheme to Phoneme Conversion

A finite-state method, based on leftmost longestmatch replacement, is presented for segmenting words into graphemes, and for converting graphemes into phonemes. A small set of hand-crafted conversion rules for Dutch achieves a phoneme accuracy of over 93%. The accuracy of the system is further improved by using transformation-based learning. The phoneme accuracy of the best system (using a large rule and a 'lazy' variant of Brill's algoritm), trained on only 40K words, reaches 99%.

[1]  Yves Schabes,et al.  Deterministic Part-of-Speech Tagging with Finite-State Transducers , 1995, Comput. Linguistics.

[2]  Karel Pala,et al.  TreeTalk-D : a Machine Learning Approach to Dutch Word Pronunciation , 1998 .

[3]  Walter Daelemans,et al.  Meta-Learning for Phonemic Annotation of Corpora , 2000, ICML.

[4]  Ken Samuel,et al.  Dialogue Act Tagging with Transformation-Based Learning , 1998, ACL.

[5]  Gregory Grefenstette,et al.  Regular expressions for language engineering , 1996, Natural Language Engineering.

[6]  Lauri Karttunen,et al.  The Replace Operator , 1995, ACL.

[7]  Richard Sproat,et al.  The bell labs German text-to-speech system: an overview , 1997, EUROSPEECH.

[8]  Walter Daelemans,et al.  Language-Independent Data-Oriented Grapheme-to-Phoneme Conversion , 1996 .

[9]  Briony Williams.  Welsh letter-to-sound rules: rewrite rules and two-level rules compared , 1994, Comput. Speech Lang..

[10]  Alan W. Black,et al.  Issues in building general letter to sound rules , 1998, SSW.

[11]  Walter Daelemans,et al.  A Rule Induction Approach to Modeling Regional Pronunciation Variation , 2000, COLING.

[12]  Gertjan van Noord,et al.  Transducers from Rewrite Rules with Backreferences , 1999, EACL.

[13]  R. H. Baayen,et al.  The CELEX Lexical Database (CD-ROM) , 1996 .

[14]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

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

[16]  Treebank Penn,et al.  Linguistic Data Consortium , 1999 .

[17]  Torbjörn Lager.  The µ-TBL System: Logic Programming Tools for Transformation-Based Learning , 1999, CoNLL.

[18]  Martin Kay,et al.  Regular Models of Phonological Rule Systems , 1994, CL.

[19]  Richard Sproat,et al.  Review of PC-KIMMO: a two-level processor for morphological analysis by Evan L. Antworth. Summer Institute of Linguistics 1990 , 1991 .

[20]  Eric Brill,et al.  Transformation-Based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-Speech Tagging , 1995, CL.

[21]  S. G. C. Lawrence,et al.  Alignment of phonemes with their corresponding orthography , 1986 .