Work

Say Again? The Limits of Whisper with Conversation. A Case Study on the KIParla Corpus.

Year: 2026

Type: conference-paper

Abstract: This study investigates how Whisper handles interactional phenomena in spontaneous Italian conversation, focusing on backchannels, repairs, and filled pauses.We compare standard Word Error Rate (WER) optimization with a decoding strategy that explicitly rewards the preservation of interactional events.Results show that decoding choices have limited impact on overall accuracy, while recognition remains strongly phenomenon-dependent, suggesting structural limitations in the handling of interactional phenomena, with systematic linearization of repairs and frequent suppression of short conversational items.

Source: Language Resources and Evaluation Conference (LREC)

DOI: 10.63317/2so5y449gb4w

Authors: Martina Simonotti, Ludovica Pannitto, Caterina Mauri, Adriano Ferraresi, Gabriele Carioli

Institution: University of Bologna

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7166524751

FWCI:

Cites:

Cited by:

Related to: 10