@InProceedings{Busch2026_1289,
author = {Matthias Busch and Jonas Schewior and Andreas Wendemuth and Ingo Siegert},
booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2026, Tagungsband der 37. Konferenz},
title = {Creating Documents with Voice: Maybe it is not about Transcription but Reflection?},
year = {2026},
editor = {Günther Wirsching},
month = mar,
pages = {143--150},
publisher = {TUDpress, Dresden},
abstract = {Traditional dictation systems implicitly treat speech as equivalent to writing, overlooking the recursive nature of composition and penalizing cognitive pauses essential for reflection. In an exploratory study (N= 10), participants dictated formal and informal emails, then compared raw transcripts, manually edited versions, and Large Language Model (LLM)-transformed variants (Llama 3.1-8B/3.3-70B). No participant preferred raw output; while LLM processing helped with formal tasks, most preferred self-edited versions for authorial control. One-shot transformation proved vulnerable to Automatic Speech Recognition (ASR) error propagation and stylistic mismatches in informal contexts. These findings motivate a thought-to-text paradigm, reconceiving dictation as collaborative composition rather than linear transcription.},
isbn = {978-3-95908-834-3},
issn = {0940-6832},
keywords = {Voice, Language and Cognition},
url = {https://www.essv.de/pdf/2026_143_150.pdf},
}