@inproceedings{e0113681a1f7487e9c5c0dd427cba625,
title = "Speak: A Toolkit Using Amazon Mechanical Turk to Collect and Validate Speech Audio Recordings",
abstract = "We present Speak, a toolkit that allows researchers to crowdsource speech audio recordings using Amazon Mechanical Turk (MTurk). Speak allows MTurk workers to submit speech recordings in response to a task prompt and stimulus (e.g. image, text excerpt, audio file) defined by researchers, a functionality that is not natively offered by MTurk at the time of writing this paper. Importantly, the toolkit employs multiple measures to ensure that speech recordings collected are of adequate quality, in order to avoid accepting unusable data and prevent abuse/fraud. Speak has demonstrated utility, having collected over 600,000 recordings to date. The toolkit is open-source and available for download.",
keywords = "crowdsourcing, data collection, human-computer interaction, speech recognition",
author = "Christopher Song and David Harwath and Tuka Alhanai and James Glass",
note = "Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.; 13th International Conference on Language Resources and Evaluation Conference, LREC 2022 ; Conference date: 20-06-2022 Through 25-06-2022",
year = "2022",
language = "English (US)",
series = "2022 Language Resources and Evaluation Conference, LREC 2022",
publisher = "European Language Resources Association (ELRA)",
pages = "7253--7258",
editor = "Nicoletta Calzolari and Frederic Bechet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Jan Odijk and Stelios Piperidis",
booktitle = "2022 Language Resources and Evaluation Conference, LREC 2022",
}