Paper: Learning from 26 Languages: Program Management and Science in the Babel Program

ACL ID C14-1001
Title Learning from 26 Languages: Program Management and Science in the Babel Program
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2014
Authors

Invited Speaker Abstract This presentation will illustrate how program management and science can cooperate to increase our understanding of human languages and algorithms for processing them. In this presentation, I will use the IARPA Babel program as an example. The goal of the Babel Program is to rapidly develop speech recognition capability for keyword search in new languages, working with speech recorded in a variety of conditions and with limited amounts of transcription. The speech data is recorded in native countries and contains variability in speaker demographics and recording conditions. The Program will ultimately address a broad set of languages with a variety of phonotactic, phonological, tonal, morphological, and syntactic characteristics. I will discuss the data resources c...