Rethinking the Joint Estimation of Magnitude and Phase for Time-frequency Domain Neural Vocoders
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 1-5
Abstract
No abstract availableAll Related Versions
Funding Information
- National Natural Science Foundation of China (62501588)
This publication has 28 references indexed in Scilit:
- BAE-Net: a Low Complexity and High Fidelity Bandwidth-Adaptive Neural Network for Speech Super-Resolution2024
- Audiosr: Versatile Audio Super-Resolution at Scale2024
- APNet2: High-Quality and High-Efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra2024
- QUICKVC: A Lightweight VITS-Based Any-to-Many Voice Conversion Model using ISTFT for Faster Conversion2023
- TF-GRIDNET: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation2023
- ISTFTNET: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform2022
- A Complex Spectral Mapping with Inplace Convolution Recurrent Neural Networks For Acoustic Echo Cancellation2022
- Fullsubnet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement2021
- Parallel Wavegan: A Fast Waveform Generation Model Based on Generative Adversarial Networks with Multi-Resolution Spectrogram2020
- LPCNET: Improving Neural Speech Synthesis through Linear Prediction2019