Phone Based Keyword Spotting for Transcribing Very Low Resource Languages

Eric Le Ferrand, Steven Bird, Laurent Besacier

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in Proceedingspeer-review

356 Downloads (Pure)

Abstract

We investigate the efficiency of two very different spoken term detection approaches for transcription when the available data is insufficient to train a robust speech recognition system. This work is grounded in a very low-resource language documentation scenario where only a few minutes of recording have been transcribed for a given language so far. Experiments on two oral languages show that a pretrained universal phone recognizer, fine-tuned with only a few minutes of target language speech, can be used for spoken term detection through searches in phone confusion networks with a lexicon expressed as a finite state automaton. Experimental results show that a phone recognition based approach provides better overall performances than Dynamic Time Warping when working with clean data, and highlight the benefits of each methods for two types of speech corpus.
Original languageEnglish
Title of host publicationProceedings of the The 19th Annual Workshop of the Australasian Language Technology Association
EditorsAfshin Rahimi, William Lane, Guido Zuccon
Place of PublicationAustralia
PublisherAustralasian Language Technology Association
Pages79-86
Number of pages8
Publication statusPublished - Dec 2021
Event19th Workshop of the Australasian Language Technology Association, ALTA 2021 - Vitual, Online, Australia
Duration: 8 Dec 202110 Dec 2021

Conference

Conference19th Workshop of the Australasian Language Technology Association, ALTA 2021
Country/TerritoryAustralia
CityVitual, Online
Period8/12/2110/12/21

Cite this