Standard

Reducing over-smoothness in speech synthesis using Generative Adversarial Networks. / Sheng, Leyuan; Pavlovskiy, Evgeniy N.

SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 972-974 8957862 (SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Harvard

Sheng, L & Pavlovskiy, EN 2019, Reducing over-smoothness in speech synthesis using Generative Adversarial Networks. in SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings., 8957862, SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 972-974, 2019 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2019, Novosibirsk, Russian Federation, 21.10.2019. https://doi.org/10.1109/SIBIRCON48586.2019.8957862

APA

Sheng, L., & Pavlovskiy, E. N. (2019). Reducing over-smoothness in speech synthesis using Generative Adversarial Networks. In SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings (pp. 972-974). [8957862] (SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIBIRCON48586.2019.8957862

Vancouver

Sheng L, Pavlovskiy EN. Reducing over-smoothness in speech synthesis using Generative Adversarial Networks. In SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 972-974. 8957862. (SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings). doi: 10.1109/SIBIRCON48586.2019.8957862

Author

Sheng, Leyuan ; Pavlovskiy, Evgeniy N. / Reducing over-smoothness in speech synthesis using Generative Adversarial Networks. SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 972-974 (SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings).

BibTeX

@inproceedings{53025969e23c46f6bd004ff9bf8d0ea8,
title = "Reducing over-smoothness in speech synthesis using Generative Adversarial Networks",
abstract = "Speech synthesis is widely used in many practical applications. In recent years, speech synthesis technology has developed rapidly. However, one of the reasons why synthetic speech is unnatural is that it often has over-smoothness. In order to improve the naturalness of synthetic speech, we first extract the mel-spectrogram of speech and convert it into a real image, then take the over-smooth mel-spectrogram image as input, and use image-To-image translation Generative Adversarial Networks(GANs) framework to generate a more realistic mel-spectrogram. Finally, the results show that this method greatly reduces the over-smoothness of synthesized speech and is more close to the mel-spectrogram of real speech.",
keywords = "GANs, mel-spectrogram, over-smoothness, Speech synthesis",
author = "Leyuan Sheng and Pavlovskiy, {Evgeniy N.}",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 2019 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2019 ; Conference date: 21-10-2019 Through 27-10-2019",
year = "2019",
month = oct,
doi = "10.1109/SIBIRCON48586.2019.8957862",
language = "English",
isbn = "978-1-7281-4402-3",
series = "SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "972--974",
booktitle = "SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings",
address = "United States",

}

RIS

TY - GEN

T1 - Reducing over-smoothness in speech synthesis using Generative Adversarial Networks

AU - Sheng, Leyuan

AU - Pavlovskiy, Evgeniy N.

N1 - Publisher Copyright: © 2019 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2019/10

Y1 - 2019/10

N2 - Speech synthesis is widely used in many practical applications. In recent years, speech synthesis technology has developed rapidly. However, one of the reasons why synthetic speech is unnatural is that it often has over-smoothness. In order to improve the naturalness of synthetic speech, we first extract the mel-spectrogram of speech and convert it into a real image, then take the over-smooth mel-spectrogram image as input, and use image-To-image translation Generative Adversarial Networks(GANs) framework to generate a more realistic mel-spectrogram. Finally, the results show that this method greatly reduces the over-smoothness of synthesized speech and is more close to the mel-spectrogram of real speech.

AB - Speech synthesis is widely used in many practical applications. In recent years, speech synthesis technology has developed rapidly. However, one of the reasons why synthetic speech is unnatural is that it often has over-smoothness. In order to improve the naturalness of synthetic speech, we first extract the mel-spectrogram of speech and convert it into a real image, then take the over-smooth mel-spectrogram image as input, and use image-To-image translation Generative Adversarial Networks(GANs) framework to generate a more realistic mel-spectrogram. Finally, the results show that this method greatly reduces the over-smoothness of synthesized speech and is more close to the mel-spectrogram of real speech.

KW - GANs

KW - mel-spectrogram

KW - over-smoothness

KW - Speech synthesis

UR - http://www.scopus.com/inward/record.url?scp=85079077606&partnerID=8YFLogxK

U2 - 10.1109/SIBIRCON48586.2019.8957862

DO - 10.1109/SIBIRCON48586.2019.8957862

M3 - Conference contribution

AN - SCOPUS:85079077606

SN - 978-1-7281-4402-3

T3 - SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings

SP - 972

EP - 974

BT - SIBIRCON 2019 - International Multi-Conference on Engineering, Computer and Information Sciences, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2019

Y2 - 21 October 2019 through 27 October 2019

ER -

ID: 28278090