BibTeX

@inProceedings{chiriatti-etal-2026-gold-367165,
	title        = {Gold-Preserving Synthetic Augmentation for Verbatim Swedish Automatic Speech Recognition},
	abstract     = {Verbatim transcripts, which keep the hesitations and interactional particles that ordinary automatic speech recognition (ASR) removes, are a prerequisite for speech-based cognitive assessment, and they are hardest to obtain for languages with little annotated speech. We study this problem for Swedish with a 1.02-hour corpus of manually transcribed spontaneous speech, too small for full fine-tuning of KB-Whisper-large. We adapt the model with a low-rank adapter and compare three ways of extending the training data: pseudo-labeling of untranscribed in-domain audio, unguided synthesis with a language model and a text-to-speech system, and a gold-preserving pipeline that reproduces the disfluency distribution of the gold corpus by construction and can be audited before training. Fine-tuning reduces disfluency-segment word error rate (WER) by 32% relative, with blockwise-bootstrap confidence intervals disjoint from the zero-shot baseline, while the three augmentation strategies are not separable by WER across five seeds. The gold-preserving pipeline needs no untranscribed audio, and its disfluency distribution can be verified in advance.},
	booktitle    = {The Proceedings of Speech and Audio Language Models Workshop (2nd Edition), October 28, 2026},
	author       = {Chiriatti, Giuseppe and Kokkinakis, Dimitrios and Bertini, Flavio and Muñoz Sánchez, Ricardo and Lange, Herbert},
	year         = {2026},
	publisher    = {Association for Computational Linguistics (ACL)},
	address      = {Kerrville, TX },
	ISBN         = {979-8-89176-496-5},
	pages        = {38--44},
}