Generative adversarial network-based approach to signal reconstruction from magnitude spectrogram

Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Hiroyasu Ando

研究成果: Conference contribution

11 被引用数 (Scopus)

抄録

In this paper, we address the problem of reconstructing a time-domain signal (or a phase spectrogram) solely from a magnitude spectrogram. Since magnitude spectrograms do not contain phase information, we must restore or infer phase information to reconstruct a time-domain signal. One widely used approach for dealing with the signal reconstruction problem was proposed by Griffin and Lim. This method usually requires many iterations for the signal reconstruction process and depending on the inputs, it does not always produce high-quality audio signals. To overcome these shortcomings, we apply a learning-based approach to the signal reconstruction problem by modeling the signal reconstruction process using a deep neural network and training it using the idea of a generative adversarial network. Experimental evaluations revealed that our method was able to reconstruct signals faster with higher quality than the Griffin-Lim method.

本文言語English
ホスト出版物のタイトル2018 26th European Signal Processing Conference, EUSIPCO 2018
出版社European Signal Processing Conference, EUSIPCO
ページ2514-2518
ページ数5
ISBN(電子版)9789082797015
DOI
出版ステータスPublished - 2018 11 29
外部発表はい
イベント26th European Signal Processing Conference, EUSIPCO 2018 - Rome, Italy
継続期間: 2018 9 32018 9 7

出版物シリーズ

名前European Signal Processing Conference
2018-September
ISSN(印刷版)2219-5491

Conference

Conference26th European Signal Processing Conference, EUSIPCO 2018
国/地域Italy
CityRome
Period18/9/318/9/7

ASJC Scopus subject areas

  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Generative adversarial network-based approach to signal reconstruction from magnitude spectrogram」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル