@inproceedings{3671461a483e43ea882677f40aa11b9d,
title = "AusKidTalk: using strategic data collection and out-of-domain tools to semi-automate novel corpora annotation",
abstract = "Annotating speech corpora for novel populations presents a circular problem: eliminating costly manual transcription requires automatic speech recognition (ASR) tools not yet developed; but developing ASR tools requires annotated speech corpora not available. Manual transcription burden was reduced for AusKidTalk, a novel population due to speaker age and accent, by strategic data collection protocol combined with out-of-domain ASR tools for semi-automatic annotation. The data collection protocol inserted tones and timestamps to automatically segment the recordings. Automatic annotation was conducted by out-of-domain tools for diarisation (NeMo) and orthographic transcription (UNSW ASR). Transcription accuracy with 17\% word error rate (WER) for single words and 23\% WER for continuous speech allowed for hand-correction instead of transcription, reducing annotation burden. The workflow can be adapted for other corpora and updated with new ASR tools as they become available.",
keywords = "Australian English, automatic speech recognition, child speech, orthographic transcription, speech corpus",
author = "T{\"u}nde Szalay and Mostafa Shahin and Tharmakulasingam Sirojan and Zheng Nan and Renata Huang and Kirrie Ballard and Beena Ahmed",
year = "2025",
doi = "10.21437/Interspeech.2025-539",
language = "English",
series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
publisher = "International Speech Communication Association (ISCA)",
pages = "4268--4272",
booktitle = "INTERSPEECH 2025",
note = "Interspeech Conference (26th : 2025) ; Conference date: 17-08-2025 Through 21-08-2025",
}