Thesis Details
Robustní detekce řečové aktivity
The aim of this work is to design and create a robust speech activity detector that is able to detect speech in different languages, in a noise environment and with music on background. I decided to solve this problem by using a neural network as a classification model that assigns one of the four possible classes - silence, speech, music, or noise to the input of audio recording. The resulting tool is able to detect the speech in at least 12 languages. Speech with musical background up to 88 % accuracy and system success on noisy data reaches from 84 % (5 dB SNR) to 88 % (20 dB SNR). This tool can be used for speech activity detection in various research areas of speech processing. The main contribution is the elimination of music, which when not eliminated, significantly increases the error rate of systems for speaker identification or speech recognition.
Robust voice activity detection, Music, Noise, Neural Network, SNR.
Bartík Vladimír, Ing., Ph.D. (DIFS FIT BUT), člen
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Meduna Alexander, prof. RNDr., CSc. (DIFS FIT BUT), člen
Smrčka Aleš, Ing., Ph.D. (DITS FIT BUT), člen
Trenz Oldřich, doc. Ing., Ph.D. (Mendelu), člen
@mastersthesis{FITMT21780,
author = "Anna Popkov\'{a}",
type = "Master's thesis",
title = "Robustn\'{i} detekce \v{r}e\v{c}ov\'{e} aktivity",
school = "Brno University of Technology, Faculty of Information Technology",
year = 2019,
location = "Brno, CZ",
language = "czech",
url = "https://www.fit.vut.cz/study/thesis/21780/"
}