Confides: A Visual Analytics Solution for Automated Speech Recognition Analysis and Exploration

TL;DR

ConFides is a visual analytics tool designed to improve the interpretation and editing of automatic speech recognition outputs by visually representing confidence scores, aiding analysts in exploration and reducing misinterpretation.

Contribution

The paper introduces ConFides, a novel visual analytic system that effectively communicates confidence scores in ASR outputs to enhance analysis and editing workflows.

Findings

ConFides helps analysts identify low-confidence transcriptions.

The system improves understanding of ASR output reliability.

It facilitates better human-AI collaboration in speech analysis.

Abstract

Confidence scores of automatic speech recognition (ASR) outputs are often inadequately communicated, preventing its seamless integration into analytical workflows. In this paper, we introduce ConFides, a visual analytic system developed in collaboration with intelligence analysts to address this issue. ConFides aims to aid exploration and post-AI-transcription editing by visually representing the confidence associated with the transcription. We demonstrate how our tool can assist intelligence analysts who use ASR outputs in their analytical and exploratory tasks and how it can help mitigate misinterpretation of crucial information. We also discuss opportunities for improving textual data cleaning and model transparency for human-machine collaboration.