How do you pronounce your name? Improving G2P with transliterations

Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, pages 399–408, Portland, Oregon, June 19-24, 2011. c⃝2011 Association for Computational Linguistics How do you pronounce your name? Improving G2P with transliterations Aditya Bhargava and Grzegorz Kondrak Department of Computing Science University of Alberta Edmonton, Alberta, Canada, T6G 2E8 {abhargava,kondrak}@cs.ualberta.ca Abstract Grapheme-to-phoneme conversion (G2P) of names is an important and challenging prob- lem. The correct pronunciation of a name is often reflected in its transliterations, which are expressed within a different phonological in- ventory. We investigate the problem of us- ing transliterations to correct errors produced by state-of-the-art G2P systems. We present a novel re-ranking approach that incorporates a variety of score and n-gram features, in order to leverage transliterations from multiple lan- guages. Our experiments demonstrate signifi- cant accuracy improvements when re-ranking is applied to n-best lists generated by three different G2P programs. 1 Introduction Grapheme-to-phoneme conversion (G2P), in which the aim is to convert the orthography of a word to its pronunciation (phonetic transcription), plays an im- portant role in speech synthesis and understanding. Names, which comprise over 75% of unseen words (Black et al., 1998), present a particular challenge to G2P systems because of their high pronunciation variability. Guessing the correct pronunciation of a name is often difficult, especially if they are of for- eign origin; this is attested by the ad hoc transcrip- tions which sometimes accompany new names intro- duced in news articles, especially for international stories with many foreign names. Transliterations provide a way of disambiguating the pronunciation of names. They are more abun- dant than phonetic transcriptions, for example when news items of international or global significance are reported in multiple languages. In addition, writing scripts such as Arabic, Korean, or Hindi are more consistent and easier to identify than various pho- netic transcription schemes. The process of translit- eration, also called phonetic translation (Li et al., 2009b), involves “sounding out” a name and then finding the closest possible representation of the sounds in another writing script. Thus, the correct pronunciation of a name is partially encoded in the form of the transliteration. For example, given the ambiguous letter-to-phoneme mapping of the En- glish letter g, the initial phoneme of the name Gersh- win may be predicted by a G2P system to be ei- ther /g/ (as in Gertrude) or /Ã/ (as in Gerald). The transliterations of the name in other scripts provide support for the former (correct) alternative. Although it seems evident that transliterations should be helpful in determining the correct pronun- ciation of a name, designing a system that takes ad- vantage of this insight is not trivial. The main source of the difficulty stems from the differences between the phonologies of distinct languages. The mappings between phonemic inventories are often complex and context-dependent. For example, because Hindi has no /w/ sound, the transliteration of Gershwin instead uses a symbol that represents the phoneme /V/, similar to the /v/ phoneme in English. In ad- dition, converting transliterations into phonemes …

Content truncated to 500 words