Longa: An automated speech recognition tool for Bantu languages

Simple item page
cg.authorship.typesCGIAR multi-centreen
cg.authorship.typesCGIAR and advanced research instituteen
cg.contributor.affiliationUniversity of Nottinghamen
cg.contributor.affiliationInternational Maize and Wheat Improvement Centeren
cg.contributor.affiliationInternational Food Policy Research Instituteen
cg.contributor.donorCGIAR Trust Funden
cg.contributor.initiativeDigital Innovation
cg.coverage.regionAfrica
cg.creator.identifierJawoo Koo: 0000-0003-3424-9229
cg.howPublishedGrey Literatureen
cg.identifier.projectIFPRI - Natural Resources and Resilience Unit
cg.identifier.projectIFPRI - Systems Transformation - Transformation Strategies
cg.identifier.publicationRankNot ranked
cg.numberDec-23en
cg.placeWashington, DCen
cg.reviewStatusInternal Reviewen
cg.subject.actionAreaSystems Transformation
cg.subject.impactAreaGender equality, youth and social inclusion
dc.contributor.authorMganga, Nelsonen
dc.contributor.authorJones-Garcia, Elioten
dc.contributor.authorMonsalue, Andrea Gardeazabalen
dc.contributor.authorKoo, Jawooen
dc.date.accessioned2024-01-04T20:42:09Zen
dc.date.available2024-01-04T20:42:09Zen
dc.identifier.urihttps://hdl.handle.net/10568/137177
dc.titleLonga: An automated speech recognition tool for Bantu languagesen
dcterms.abstractFarm Radio International (FRI) and the CGIAR Research Initiative on Digital Innovation have col laborated on the development of an end-to-end, automatic speech recognition pipeline for the tran scription, translation, and analysis of Swahili and Luganda. This task is particularly challenging due to the number of languages used by FRI's clients and the limited training data available for speech recognition in African languages. The tool is named 'Longa', or 'Let's chat' in Swahili. Longa will be used to answer the surplus of phone calls currently being received from smallholder farmers asking questions about radio programs which FRI does not presently have the capacity to address. When fully implemented, Longa should allow FRI to design their broadcasts more intricately in line with the needs of farmers and better deliver insights to those most in need, such as female and youth farmers. Key results from the collaboration include a series of design principles iteratively and col laboratively developed to reflect the common values and goals of FRI and the CGIAR, a proof of concept for Longa, building on open-source models and open access corpora, to be shared with the developer community upon completion of the final tool, a 10% improvement upon the state-of-the art automatic speech recognition in Luganda radio-speech performance and accuracy, some im provement in performance with audio enhancement processes using real-world data, and proof that fine-tuning is an effective approach to expanding Longa to new languages. The next steps of the collaboration will focus on the analysis and interpretation of an aggregation of farmer phone calls and integration with the existing FRI workflow and software.en
dcterms.accessRightsOpen Access
dcterms.audienceCGIARen
dcterms.bibliographicCitationMganga, Nelson; Jones-Garcia, Eliot; Monsalue, Andrea Gardeazabal; and Koo, Jawoo. 2023. Longa: An automated speech recognition tool for Bantu languages. Digital Innovation Technical Report December 2023. Washington, DC: International Food Policy Research Institute (IFPRI). https://hdl.handle.net/10568/137177en
dcterms.extent13 p.en
dcterms.isPartOfDigital Innovation Technical Reporten
dcterms.issued2023-12-31
dcterms.languageen
dcterms.licenseCC-BY-4.0
dcterms.publisherInternational Food Policy Research Instituteen
dcterms.replaceshttps://ebrary.ifpri.org/digital/collection/p15738coll2/id/137071en
dcterms.subjectartificial intelligenceen
dcterms.subjectinnovation adoptionen
dcterms.subjectlanguagesen
dcterms.subjectfarmersen
dcterms.typeReport

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Eliot Jones (2023) -- Technical Report -- AI Farm Radio.pdf
Size:
2.45 MB
Format:
Adobe Portable Document Format
Description:
Technical Report
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.75 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

IFPRI Project Papers
CGIAR Initiative on Digital Innovation