2017 INTERSPEECH INTERSPEECH 2017

WebSubDub — Experimental System for Creating High-Quality Alternative Audio Track for TV Broadcasting

Abstract

This paper deals with a presentation of an experimental system (called WebSubDub) for creating a high-quality alternative audio track for TV broadcasting. The system is used to create subtitles for TV shows in such a format which allows to automatically generate an alternative audio track with multiple voices employing a specially adapted TTS system. This alternative audio track is intended for televiewers with slight hearing impairments, i.e. for a group of televiewers who encounter issues when perceiving the original audio track — especially dialogues with background music, background noise or emotional speech. The system was developed in cooperation with Czech television, the public service broadcaster in the Czech Republic.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Machine Learning
🧭 Keyword Pioneer — alternative audio track
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Interdisciplinary, Machine Learning, Natural Language Processing, Reinforcement Learning, Speech & Audio