A new method for OOV detection using hybrid word/fragment system

Author

Rastrow, Ariya ; Sethy, Abhinav ; Ramabhadran, Bhuvana

Author_Institution

Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD

fYear

2009

fDate

19-24 April 2009

Firstpage

3953

Lastpage

3956

Abstract

In this paper, we propose a new method for detecting regions with out-of-vocabulary (OOV) words in the output of a large vocabulary continuous speech recognition (LVCSR) system. The proposed method uses a hybrid system combining words and data-driven variable length sub word units. With the use of a single feature, the posterior probability of sub word units, this method outperforms existing methods published in the literature. We also presents a recipe to discriminatively train a hybrid language model to improve OOV detection rate. Results are presented on the RT04 broadcast news task.

Keywords

speech recognition; OOV detection; discriminative training; hybrid system; large vocabulary continuous speech recognition; out-of-vocabulary words; Acoustic measurements; Acoustic signal detection; Automatic speech recognition; Error analysis; Error correction; Natural languages; Speech recognition; Statistics; Training data; Vocabulary; OOV; discriminative training; hybrid ASR system; out-of-vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on

Conference_Location

Taipei

ISSN

1520-6149

Print_ISBN

978-1-4244-2353-8

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2009.4960493

Filename

4960493