Real-Time Signal Estimation From Modified Short-Time Fourier Transform Magnitude Spectra

142 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

SIGNAL RECONSTRUCTION FROM STFT MAGNITUDE : A STATE OF THE ART (2011, background): “[23] proposed two implementations of the reconstruction, starting with a constraint of a real-time implementation.”
A Comparison of Recent Neural Vocoders for Speech Signal Reconstruction (2019, background): “Since the iterative phase estimates can only converge to local optima, several publications were concerned with finding a good initial estimate for the phase information [23, 24].”
Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention (2017, methodology): “We always use RTISI-LA [29], an online GLA, to synthesize a waveform.”
Phase Processing for Single-Channel Speech Enhancement: History and recent advances (2015, methodology): “[17] proposed to partially compensate by using asymmetric analysis windows with a reverse effect.”
End-To-End Speech Synthesis Applied to Brazilian Portuguese (2020, methodology): “DCTTS uses the vocoder RTISI-LA (Real-Time Iterative Spectrogram Inversion with Look-Ahead) [Zhu et al., 2007], which is an adaptation of the Griffin-Lim vocoder [Griffin and Lim, 1984], which aims to increase the speed of the synthesis by slightly sacrificing the quality of the audio generated.”