CACTAS - Collaborative Audio Categorization and Transcription for ASR Systems

Mithul Mathivanan, Kinnera Saranu, Abhishek Pandey and Jithendra Vepa

Abstract:

We present a web based tool that allows collaborative analysis and/or transcription of audios with respect to Automatic Speech Recognition (ASR) systems. The tool presents a webpage consisting of audios and their corresponding references and hypotheses obtained offline. Several other information and features are provided that allow the audios to be categorized and references to be corrected efficiently in a collaborative way almost 10 times faster, without the need for prior knowledge on speech or ASR systems. The analysis can later be summarized and acted upon to improve or triage the ASR system.

---

Cite as: Mathivanan, M., Saranu, K., Pandey, A., Vepa, J. (2018) CACTAS - Collaborative Audio Categorization and Transcription for ASR Systems. Proc. Interspeech 2018, 1495-1496.

---

BiBTeX Entry:

@inproceedings{Mathivanan2018,
author={Mithul Mathivanan and Kinnera Saranu and Abhishek Pandey and Jithendra Vepa},
title={CACTAS - Collaborative Audio Categorization and Transcription for ASR Systems},
year=2018,
booktitle={Proc. Interspeech 2018},
pages={1495--1496} }