No Cover Image

Conference Paper/Proceeding/Abstract 584 views 60 downloads

Situating Automatic Speech Recognition Development within Communities of Under-heard Language Speakers

Thomas Reitmaier Orcid Logo, Electra Wallington, Ondrej Klejch, Nina Markl, Léa-Marie Lam-Yee-Mui, Jen Pearson Orcid Logo, Matt Jones Orcid Logo, Peter Bell, Simon Robinson Orcid Logo

ACM CHI Conference on Human Factors in Computing Systems: CHI' 23, Pages: 1 - 17

Swansea University Authors: Thomas Reitmaier Orcid Logo, Jen Pearson Orcid Logo, Matt Jones Orcid Logo, Simon Robinson Orcid Logo

DOI (Published version): 10.1145/3544548.3581385

Abstract

In this paper we develop approaches to automatic speech recognition (ASR) development that suit the needs and functions of underheard language speakers. Our novel contribution to HCI is to show how community-engagement can surface key technical and social issues and opportunities for more efective s...

Full description

Published in: ACM CHI Conference on Human Factors in Computing Systems: CHI' 23
ISBN: 978-1-4503-9421-5/23/04
Published: ACM 2023
URI: https://cronfa.swan.ac.uk/Record/cronfa62395
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: In this paper we develop approaches to automatic speech recognition (ASR) development that suit the needs and functions of underheard language speakers. Our novel contribution to HCI is to show how community-engagement can surface key technical and social issues and opportunities for more efective speech-based systems. We introduce a bespoke toolkit of technologies and showcase how we utilised the toolkit to engage communities of under-heard language speakers; and, through that engagement process, situate key aspects of ASR development in community contexts. The toolkit consists of (1) an information appliance to facilitate spoken-data collection on topics of community interest, (2) a mobile app to create crowdsourced transcripts of collected data, and (3) demonstrator systems to showcase ASR capabilities and to feed back research results to community members. Drawing on the sensibilities we cultivated through this research, we present a series of challenges to the orthodoxy of state-of-the-art approaches to ASR development.
Keywords: Text/speech/language, automatic speech recognition, mobile devices: phones/tablets
College: Faculty of Science and Engineering
Funders: UKRI (EP/T024976/1)
Start Page: 1
End Page: 17