Google´s cross-dialect Arabic voice search

Author

Biadsy, Fadi ; Moreno, Pedro J. ; Jansche, Martin

Author_Institution

Google Inc., New York, NY, USA

fYear

2012

fDate

25-30 March 2012

Firstpage

4441

Lastpage

4444

Abstract

We present a large scale effort to build a commercial Automatic Speech Recognition (ASR) product for Arabic. Our goal is to support voice search, dictation, and voice control for the general Arabic-speaking public, including support for multiple Arabic dialects. We describe our ASR system design and compare recognizers for five Arabic dialects, with the potential to reach more than 125 million people in Egypt, Jordan, Lebanon, Saudi Arabia, and the United Arab Emirates (UAE). We compare systems built on diacritized vs. non-diacritized text. We also conduct cross-dialect experiments, where we train on one dialect and test on the others. Our average word error rate (WER) is 24.8% for voice search.

Keywords

error statistics; natural languages; search engines; speech recognition; Arabic dialects; Google crossdialect Arabic voice search; automatic speech recognition; dictation; nondiacritized text; voice control; word error rate; Acoustics; Speech; Speech recognition; System analysis and design; Testing; Training; Arabic; Speech Recognition; Voice Search;

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.2012.6288905

Filename

6288905