A comparison of online automatic speech recognition systems

Joshua Yee Kim, Chunfeng Lui, Rafael A. Calvo, Kathryn McCabe, Silas CR Taylor, Bjorn Schuller, Kaihang Wu

Abstract:

High-quality transcription systems are required for conversational
analysis systems. We compared two manual transcribers with five automatic transcription systems using video-conferences from a medical domain and found that
(1) manual transcriptions significantly outperformed the automatic services, and
(2) the automatic transcription of YouTube Captions significantly outperformed the other ASR services