@inproceedings{31210b10deeb4de689510a67865b3c56,
title = "Comparison of Forced-Alignment Speech Recognition and Humans for Generating Reference VAD",
abstract = "This present paper aims to answer the question whether forced-alignment speech recognition can be used as an alternative to humans in generating reference Voice Activity Detection (VAD) transcriptions. An investigation of the level of agreement between automatic/manual VAD transcriptions and the reference ones produced by a human expert was carried out. Thereafter, statistical analysis was employed on the automatically produced and the collected manual transcriptions. Experimental results confirmed that forced-alignment speech recognition can provide accurate and consistent VAD labels.",
author = "Ivan Kraljevski and Zheng-Hua Tan and {Paola Bissiri}, Maria",
year = "2015",
language = "English",
series = "INTERSPEECH ",
publisher = "ISCA",
pages = "2937--2941",
booktitle = "INTERSPEECH-2015",
note = "INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association ; Conference date: 06-09-2015 Through 10-09-2015",
}