Enabling interactive transcription in an Indigenous community

Eric Le Ferrand; Steven Bird

Enabling interactive transcription in an Indigenous community

CDU Higher Degree by Research (HDR) Cohort

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

Abstract

We propose a novel transcription workflow which combines spoken term detection and human-in-the-loop, together with a pilot experiment. This work is grounded in an almost zero-resource scenario where only a few terms have so far been identified, involving two endangered languages. We show that in the early stages of transcription, when the available data is insufficient to train a robust ASR system, it is possible to take advantage of the transcription of a small number of isolated words in order to bootstrap the transcription of a speech collection.

Original language	English
Title of host publication	Proceedings of the 28th International Conference on Computational Linguistics
Pages	3422-3428
Number of pages	7
Publication status	Published - 2020
Event	The 28th International Conference on Computational Linguistics: COLING 2020 - Barcelona, Spain Duration: 8 Dec 2020 → 13 Dec 2020 https://www.aclweb.org/anthology/2020.coling-main.0.pdf

Conference

Conference	The 28th International Conference on Computational Linguistics
Country	Spain
City	Barcelona
Period	8/12/20 → 13/12/20
Internet address	https://www.aclweb.org/anthology/2020.coling-main.0.pdf

Access to Document

Cite this

@inproceedings{8e62475f2d5644ac8ba1883239dda248,

title = "Enabling interactive transcription in an Indigenous community",

abstract = "We propose a novel transcription workflow which combines spoken term detection and human-in-the-loop, together with a pilot experiment. This work is grounded in an almost zero-resource scenario where only a few terms have so far been identified, involving two endangered languages. We show that in the early stages of transcription, when the available data is insufficient to train a robust ASR system, it is possible to take advantage of the transcription of a small number of isolated words in order to bootstrap the transcription of a speech collection.",

author = "{Le Ferrand}, Eric and Steven Bird",

year = "2020",

language = "English",

isbn = "978-1-952148-27-9",

pages = "3422--3428",

booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",

note = "The 28th International Conference on Computational Linguistics : COLING 2020 ; Conference date: 08-12-2020 Through 13-12-2020",

url = "https://www.aclweb.org/anthology/2020.coling-main.0.pdf",

}

TY - GEN

T1 - Enabling interactive transcription in an Indigenous community

AU - Le Ferrand, Eric

AU - Bird, Steven

PY - 2020

Y1 - 2020

N2 - We propose a novel transcription workflow which combines spoken term detection and human-in-the-loop, together with a pilot experiment. This work is grounded in an almost zero-resource scenario where only a few terms have so far been identified, involving two endangered languages. We show that in the early stages of transcription, when the available data is insufficient to train a robust ASR system, it is possible to take advantage of the transcription of a small number of isolated words in order to bootstrap the transcription of a speech collection.

AB - We propose a novel transcription workflow which combines spoken term detection and human-in-the-loop, together with a pilot experiment. This work is grounded in an almost zero-resource scenario where only a few terms have so far been identified, involving two endangered languages. We show that in the early stages of transcription, when the available data is insufficient to train a robust ASR system, it is possible to take advantage of the transcription of a small number of isolated words in order to bootstrap the transcription of a speech collection.

UR - https://www.aclweb.org/anthology/2020.coling-main.0.pdf

M3 - Conference Paper published in Proceedings

SN - 978-1-952148-27-9

SP - 3422

EP - 3428

BT - Proceedings of the 28th International Conference on Computational Linguistics

T2 - The 28th International Conference on Computational Linguistics

Y2 - 8 December 2020 through 13 December 2020

ER -

Enabling interactive transcription in an Indigenous community

Abstract

Conference

Access to Document

Fingerprint

Cite this