Grapheme-to-phoneme model generation for Indo-European languages

Author

Schlippe, Tim ; Ochs, Sebastian ; Schultz, Tanja

Author_Institution

Cognitive Syst. Lab., Karlsruhe Inst. of Technol. (KIT), Karlsruhe, Germany

fYear

2012

fDate

25-30 March 2012

Firstpage

4801

Lastpage

4804

Abstract

In this paper, we evaluate grapheme-to-phoneme (g2p) models among languages and of different quality. We created g2p models for Indo-European languages with word-pronunciation pairs from the GlobalPhone project and from Wiktionary [1]. Then we checked their quality in terms of consistency and complexity as well as their impact on Czech, English, French, Spanish, Polish, and German ASR. While the GlobalPhone dictionaries were manually cross-checked and have been used successfully in LVCSR, Wiktionary pronunciations have been provided by the Internet community and can be used to rapidely and economically create pronunciation dictionaries for new languages and domains.

Keywords

Internet; computational complexity; dictionaries; natural language processing; speech recognition; Czech ASR; English ASR; French ASR; German ASR; GlobalPhone dictionaries; GlobalPhone project; Indo-European languages; Internet community; LVCSR; Polish ASR; Spanish ASR; Wiktionary pronunciations; automatic speech recognition; complexity check; consistency check; g2p model; grapheme-to-phoneme model generation; multilingual speech recognition; word-pronunciation pairs; Complexity theory; Computational modeling; Data models; Dictionaries; Error analysis; Training; Training data; multilingual speech recognition; pronunciation modeling; web-derived pronunciations;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on

Conference_Location

Kyoto

ISSN

1520-6149

Print_ISBN

978-1-4673-0045-2

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2012.6288993

Filename

6288993