@inproceedings{9f293a21cde1446eb817cf5861382bc1,
title = "A complete end-to-end speaker verification system using deep neural networks: From raw signals to verification result",
abstract = "End-to-end systems using deep neural networks have been widely studied in the field of speaker verification. Raw audio signal processing has also been widely studied in the fields of automatic music tagging and speech recognition. However, as far as we know, end-to-end systems using raw audio signals have not been explored in speaker verification. In this paper, a complete end-to-end speaker verification system is proposed, which inputs raw audio signals and outputs the verification results. A pre-processing layer and the embedded speaker feature extraction models were mainly investigated. The proposed pre-emphasis layer was combined with a strided convolution layer for pre-processing at the first two hidden layers. In addition, speaker feature extraction models using convolutionallayer and long short-term memory are proposed to be embedded in the proposed end-to-end system.",
keywords = "End-to-end system, Raw audio signal, Speaker verification",
author = "Jung, {Jee Weon} and Heo, {Hee Soo} and Yang, {Il Ho} and Shim, {Hye Jin} and Yu, {Ha Jin}",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 ; Conference date: 15-04-2018 Through 20-04-2018",
year = "2018",
month = sep,
day = "10",
doi = "10.1109/ICASSP.2018.8462575",
language = "English",
isbn = "9781538646588",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5349--5353",
booktitle = "2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings",
address = "United States",
}