Is Semi-Automatic Transcription Useful in Corpus Creation? Preliminary Considerations on the KIParla Corpus

TL;DR

This study evaluates the usefulness of integrating Automatic Speech Recognition into the transcription process of the KIParla Italian spoken corpus, highlighting speed gains and variable accuracy impacts depending on context and expertise.

Contribution

It provides a systematic framework for analyzing ASR-assisted transcription workflows and assesses their potential to speed up corpus creation without losing quality.

Findings

ASR-assisted workflows increase transcription speed

Accuracy improvements are inconsistent and context-dependent

Framework enables monitoring of transcription behavior

Abstract

This paper analyses the implementation of Automatic Speech Recognition (ASR) into the transcription workflow of the KIParla corpus, a resource of spoken Italian. Through a two-phase experiment, 11 expert and novice transcribers produced both manual and ASR-assisted transcriptions of identical audio segments across three different types of conversation, which were subsequently analyzed through a combination of statistical modeling, word-level alignment and a series of annotation-based metrics. Results show that ASR-assisted workflows can increase transcription speed but do not consistently improve overall accuracy, with effects depending on multiple factors such as workflow configuration, conversation type and annotator experience. Analyses combining alignment-based metrics, descriptive statistics and statistical modeling provide a systematic framework to monitor transcription behavior across annotators and workflows. Despite limitations, ASR-assisted transcription, potentially supported by task-specific fine-tuning, could be integrated into the KIParla transcription workflow to accelerate corpus creation without compromising transcription quality.