Developing Resources for Automated Speech Processing of the African Language Naija (Nigerian Pidgin)

Abstract : The development of HLT tools inevitably involves the need for language resources. However, only a handful number of languages possesses such resources. This paper presents the development of HLT tools for the African language Naija (Nigerian Pidgin), spoken in Nigeria. Particularly, this paper is focusing on developing language resources for a tokenizer, an automatic speech system for predicting the pronunciation of the words and their segmentation. The newly created resources are integrated into SPPAS software tool and distributed under the terms of public licenses.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01705707
Contributor : Brigitte Bigi <>
Submitted on : Friday, February 9, 2018 - 4:46:53 PM
Last modification on : Thursday, February 15, 2018 - 1:11:12 AM
Long-term archiving on : Saturday, May 5, 2018 - 2:22:46 AM

File

bigi2017ltc.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01705707, version 1

Collections

Citation

Brigitte Bigi, Bernard Caron, Oyelere Abiola. Developing Resources for Automated Speech Processing of the African Language Naija (Nigerian Pidgin). 8th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics, Nov 2017, Poznan, Poland. pp.441-445. ⟨hal-01705707⟩

Share

Metrics

Record views

155

Files downloads

128