A Two-Stage Neural Network for Speech Signal Reconstruction from Mel Spectrograms
- 24 May 2025
- book chapter
- Published by Springer Nature
- p. 267-278
Abstract
No abstract availableKeywords
This publication has 12 references indexed in Scilit:
- Towards real-world objective speech quality and intelligibility assessment using speech-enhancement residuals and convolutional long short-term memory networksThe Journal of the Acoustical Society of America, 2020
- Deep Griffin–Lim Iteration: Trainable Iterative Phase Reconstruction Using Neural NetworkIEEE Journal of Selected Topics in Signal Processing, 2020
- Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- Waveglow: A Flow-based Generative Network for Speech Synthesis2019
- On the Role of Linear, Mel and Inverse-Mel Filterbank in the Context of Automatic Speech Recognition2019
- Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions2018
- A fast Griffin-Lim algorithm2013
- Nonnegative Least-Mean-Square AlgorithmIEEE Transactions on Signal Processing, 2011
- On the inversion of Mel-frequency cepstral coefficients for speech enhancement applications2008
- Signal estimation from modified short-time Fourier transformIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984