A GrAF-compliant Indonesian Speech Recognition Web Service on the Language Grid for Transcription Crowdsourcing
Bayu Distiawan, Hendra Manurung · Linguistic Annotation Workshop · 2012
This paper describes the development of an Indonesian speech recognition web service which complies with two standards: it operates on the Language Grid, ensuring process interoperability, and its output uses the LAF/GrAF format, ensuring data interoperability. It is part of a larger system, currently in development, that aims to collect speech transcriptions via crowdsourcing methods. Its utility is twofold: it exposes a functional speech recognizer to the web, and allows the incremental construction of a large speech corpus.