Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Fast Development of ASR in African Languages using Self Supervised Speech Representation Learning

Domain:

natural language processing

Record type:

project
Creator:
MohThoNdoBes
Publisher:
arXiv
Host:avatar
This paper describes the results of an informal collaboration launched during the African Master of Machine Intelligence (AMMI) in June 2020. After a series of lectures and labs on speech data collection using mobile applications and on self-supervised representation learning from speech, a small group of students and the lecturer continued working on automatic speech recognition (ASR) project for three languages: Wolof, Ga, and Somali. This paper describes how data was collected and ASR systems developed with a small amount (1h) of transcribed speech as training data. In these low resource conditions, pre-training a model on large amounts of raw speech was fundamental for the efficiency of ASR systems developed. Accepted at AfricaNLP2021 workshop at EACL 2021

Visit

doi.orgarxiv.org

Tasks

automatic speech recognitionspeech processing

Languages

SomaliWolof

Tags

Sound (cs.SD)Computation and Language (cs.CL)Audio and Speech Processing (eess.AS)FOS: Computer and information sciencesFOS: Computer and information sciencesFOS: Electrical engineering, electronic engineering, information engineeringFOS: Electrical engineering, electronic engineering, information engineering

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similar

AfriHuBERT: A self-supervised speech representation model for African languagesEnsemble of learning in Self-supervised speech recognitionSemi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced LanguagesLarge vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learningMultilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitchingAutomatic Speech Recognition for Amharic Language using Self-Supervised

AfriHuBERT: A self-supervised speech representation model for African languages

In this work, we present AfriHuBERT, an extension of mHuBERT-147, a compact self-supervised learning

Ensemble of learning in Self-supervised speech recognition

Ensemble of learning in Self-supervised speech recognition

Poster presented at the Deep Learning Indaba 2023 by Ussen Kimanuka

Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages

This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages. Two approaches are considered. The first constructs four separate bilingual automatic speech recognisers

Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning

Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide pathways to large vocabular

Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching

While many speakers of low-resource languages regularly code-switch between their languages and othe

Automatic Speech Recognition for Amharic Language using Self-Supervised

Automatic Speech Recognition (ASR) systems have become a very natural human-machine interaction in w