Accession Number:

AD1040155

Title:

Code-switched English Pronunciation Modeling for Swahili Spoken Term Detection (Pub Version, Open Access)

Descriptive Note:

Journal Article

Corporate Author:

North-West University Vanderbijlpark South Africa

Report Date:

2016-05-03

Pagination or Media Count:

8.0

Abstract:

We investigate modeling strategies for English code-switched words as found in a Swahili spoken term detection system. Code switching, where speakers switch language in a conversation, occurs frequently in multilingual environments, and typically deteriorates STD performance. Analysis is performed in the context of the IARPA Babel program which focuses on rapid STD system development for under-resourced languages. Our results show that approaches that specifically target the modeling of code-switched words, significantly improve the detection performance of these words.

Subject Categories:

  • Linguistics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE