TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Noise-Robust Detection of Whispering in Telephone Calls Using Deep Neural Networks

Tutkimustuotosvertaisarvioitu

Standard

Noise-Robust Detection of Whispering in Telephone Calls Using Deep Neural Networks. / Diment, Aleksandr; Virtanen, Tuomas; Parviainen, Mikko; Zelov, Roman; Glasman, Alex.

24th European Signal Processing Conference (EUSIPCO). Budapest, Hungary : IEEE, 2016.

Tutkimustuotosvertaisarvioitu

Harvard

Diment, A, Virtanen, T, Parviainen, M, Zelov, R & Glasman, A 2016, Noise-Robust Detection of Whispering in Telephone Calls Using Deep Neural Networks. julkaisussa 24th European Signal Processing Conference (EUSIPCO). IEEE, Budapest, Hungary, EUROPEAN SIGNAL PROCESSING CONFERENCE, 1/01/00. https://doi.org/10.1109/EUSIPCO.2016.7760661

APA

Diment, A., Virtanen, T., Parviainen, M., Zelov, R., & Glasman, A. (2016). Noise-Robust Detection of Whispering in Telephone Calls Using Deep Neural Networks. teoksessa 24th European Signal Processing Conference (EUSIPCO) Budapest, Hungary: IEEE. https://doi.org/10.1109/EUSIPCO.2016.7760661

Vancouver

Diment A, Virtanen T, Parviainen M, Zelov R, Glasman A. Noise-Robust Detection of Whispering in Telephone Calls Using Deep Neural Networks. julkaisussa 24th European Signal Processing Conference (EUSIPCO). Budapest, Hungary: IEEE. 2016 https://doi.org/10.1109/EUSIPCO.2016.7760661

Author

Diment, Aleksandr ; Virtanen, Tuomas ; Parviainen, Mikko ; Zelov, Roman ; Glasman, Alex. / Noise-Robust Detection of Whispering in Telephone Calls Using Deep Neural Networks. 24th European Signal Processing Conference (EUSIPCO). Budapest, Hungary : IEEE, 2016.

Bibtex - Lataa

@inproceedings{471ac575f23f490f848ff8beae53a3c7,
title = "Noise-Robust Detection of Whispering in Telephone Calls Using Deep Neural Networks",
abstract = "Detection of whispered speech in the presence of high levels of background noise has applications in fraudulent behaviour recognition. For instance, it can serve as an indicator of possible insider trading. We propose a deep neural network (DNN)-based whispering detection system, which operates on both magnitude and phase features, including the group delay feature from all-pole models (APGD). We show that the APGD feature outperforms the conventional ones. Trained and evaluated on the collected diverse dataset of whispered and normal speech with emulated phone line distortions and significant amounts of added background noise, the proposed system performs with accuracies as high as 91.8{\%}.",
keywords = "whispering, noise robustness, deep neural networks",
author = "Aleksandr Diment and Tuomas Virtanen and Mikko Parviainen and Roman Zelov and Alex Glasman",
year = "2016",
month = "8",
day = "1",
doi = "10.1109/EUSIPCO.2016.7760661",
language = "English",
publisher = "IEEE",
booktitle = "24th European Signal Processing Conference (EUSIPCO)",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Noise-Robust Detection of Whispering in Telephone Calls Using Deep Neural Networks

AU - Diment, Aleksandr

AU - Virtanen, Tuomas

AU - Parviainen, Mikko

AU - Zelov, Roman

AU - Glasman, Alex

PY - 2016/8/1

Y1 - 2016/8/1

N2 - Detection of whispered speech in the presence of high levels of background noise has applications in fraudulent behaviour recognition. For instance, it can serve as an indicator of possible insider trading. We propose a deep neural network (DNN)-based whispering detection system, which operates on both magnitude and phase features, including the group delay feature from all-pole models (APGD). We show that the APGD feature outperforms the conventional ones. Trained and evaluated on the collected diverse dataset of whispered and normal speech with emulated phone line distortions and significant amounts of added background noise, the proposed system performs with accuracies as high as 91.8%.

AB - Detection of whispered speech in the presence of high levels of background noise has applications in fraudulent behaviour recognition. For instance, it can serve as an indicator of possible insider trading. We propose a deep neural network (DNN)-based whispering detection system, which operates on both magnitude and phase features, including the group delay feature from all-pole models (APGD). We show that the APGD feature outperforms the conventional ones. Trained and evaluated on the collected diverse dataset of whispered and normal speech with emulated phone line distortions and significant amounts of added background noise, the proposed system performs with accuracies as high as 91.8%.

KW - whispering, noise robustness, deep neural networks

U2 - 10.1109/EUSIPCO.2016.7760661

DO - 10.1109/EUSIPCO.2016.7760661

M3 - Conference contribution

BT - 24th European Signal Processing Conference (EUSIPCO)

PB - IEEE

CY - Budapest, Hungary

ER -