Generative adversarial network-based approach to signal reconstruction from magnitude spectrogram
By Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Hiroyasu Ando. 2018
33 citations recorded by the source corpus.
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.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Hubert Siuzdak
- Takuhiro Kaneko
- Hirokazu Kameoka
- Paarth Neekhara
- Chris Donahue
- Kou Tanaka
- Julian McAuley
- Shlomo Dubnov
Citations in the corpus
- Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis (2023, methodology): “Also, the initial studies using GANs to generate invertible spectrograms involved estimating instantaneous frequency (Engel et al., 2018).”
- Expediting TTS Synthesis with Adversarial Vocoding (2019, methodology): “4GANs have been previously used for phase estimation [11] and to enhance speech both before [15] and after [16] vocoding.”
- ISTFTNET: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform (2022, methodology): “The use of iSTFT for neural speech synthesis was previously introduced [26, 27, 28] (including our own early attempts [26]).”