Abstract
Constructing a pronunciation lexicon with variants in a fully automatic and language-independent way is a challenge, with many uses in human language technologies. Moreover, with the growing use of web data, there is a recurrent need to add words to existing pronunciation lexicons, and an automatic method can greatly simplify the effort required to generate pronunciations for these out-of-vocabulary words. In this paper, a machine translation approach is used to perform grapheme-to-phoneme (g2p) conversion, the task of finding the pronunciation of a word from its written form. Two alternative methods are proposed to derive pronunciation variants. In the first case, an n-best pronunciation list is extracted directly from the g2p converter. The second is a novel method based on a pivot approach, traditionally used for the paraphrase extraction task, and applied as a post-processing step to the g2p converter. The performance of these two methods is compared under different training conditions. The range of applications which require pronunciation lexicons is discussed and the generated pronunciations are further tested in some preliminary automatic speech recognition experiments.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bannard, C., Callison-Burch, C.: Paraphrasing with bilingual parallel corpora. In: Proc. of ACL (2005)
Bisani, M., Ney, H.: Investigations on Joint-Multigram Models for Grapheme-to-Phoneme Conversion. In: ICSLP, pp. 105–108 (2002)
Deligne, S., Yvon, F., Bimbot, F.: Variable-length sequence matching for phonetic transcription using joint multigrams. In: Proc. European Conf. on Speech Communication and Technology, pp. 2243–2246 (1995)
Dietterich, T.G., Bakiri, G.: Solving Multiclass Learning Problems via Error-Correcting Output Codes. Journal of Artificial Intelligence 2, 263–286 (1995)
Gauvain, J.L., Lamel, L., Adda, G.: The LIMSI Broadcast News Transcription System. Speech Comm. 37, 89–108 (2002)
Gerosa, M., Federico, M.: Coping with out-of-vocabulary words:open versus huge vocabulary ASR. In: ICASSP (2009)
Jiampojamarn, S., Cherry, C., Kondrak, G.: Joint processing and discriminative training for letter-to-phoneme conversion. In: Proc. of ACL-HLT, pp. 905–913 (2008)
Kaisse, E.M.: Word-Formation and Phonology. In: Handbook of Word-Formation, Studies in Natural Language and Linguistic Theory, vol. 64, pp. 25–47. Springer, Netherlands (2005)
Koehn, P., et al.: Moses: Open source toolkit for statistical machine translation. In: ICSLP (2002)
Lamel, L., Adda, G.: On designing pronunciation lexicons for large vocabulary, continuous speech recognition. In: Proc. ICSLP, pp. 6–9 (1996)
Laurent, A., Deleglise, P., Meignier, S.: Grapheme to phoneme conversion using an SMT system. In: Interspeech (2009)
Lee, K.F., Hon, H.W.: Speaker-Independent Phone Recognition Using Hidden Markov Models. IEEE Trans. ASSP 37(11), 1641–1648 (1989)
Mangu, L., Brill, E., Stolcke, A.: Finding Consensus Among Words: Lattice-Based Word Error Minimization. In: Eurospeech, pp. 495–498 (1999)
Rama, T., Singh, A.K., Kolachina, S.: Modeling Letter-to-Phoneme Conversion as a Phrase Based Statistical Machine Translation Problem with Minimum Error Rate Training. In: Proc. NAACL-HLT: Student Research Workshop & Doctoral Consortium, pp. 90–95 (2009)
Van Rijsbergen, C.J.: Information Retrieval, Butterworths, London, UK (1979)
Sejnowski, T., Rosenberg, C.: NETtalk: a parallel network that learns to read aloud. In: Report JHU/EECS-86/01 (1986)
Stolcke, A.: SRILM-An extensible language modeling toolkit. Proc. ICSLP 2002 (2002)
Taylor, P.: Hidden Markov models for grapheme to phoneme conversion. In: Interspeech, pp. 1973–1976 (2005)
van Berkel, B., De Smedt, K.: Triphone analysis:a combined method for the correction of orthographical and typographical errors. In: Proc. of the Second Conf. on Applied Natural Language Processing, pp. 77–83 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Karanasou, P., Lamel, L. (2011). Automatic Generation of a Pronunciation Dictionary with Rich Variation Coverage Using SMT Methods. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2011. Lecture Notes in Computer Science, vol 6609. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19437-5_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-19437-5_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19436-8
Online ISBN: 978-3-642-19437-5
eBook Packages: Computer ScienceComputer Science (R0)