No article text was recorded for this version.
spectral over-smoothing
Version 1 of 122 papers23 conceptsfrozen 2026-10-04
Papers in this version
- Blog: MetaSpeech: Speech Effects Switch Along with Environment for Metaverse
- Blog: Beyond bandlimited sampling of speech spectral envelope imposed by the harmonic structure of voiced sounds
- Blog: UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation
- Blog: MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling
- Blog: Taco-VC: A Single Speaker Tacotron based Voice Conversion with Limited Data
- Blog: SingGAN: Generative Adversarial Network For High-Fidelity Singing Voice Generation
- Blog: Recognition-Synthesis Based Non-Parallel Voice Conversion with Adversarial Learning
- Blog: DiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversion
- Blog: Denoising Recurrent Neural Network for Deep Bidirectional LSTM Based Voice Conversion
- Blog: APNet: An All-Frame-Level Neural Vocoder Incorporating Direct Prediction of Amplitude and Phase Spectra
- Blog: Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Network
- Blog: Flow-Based Unconstrained Lip to Speech Generation
- Blog: Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations
- Blog: FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis
- Blog: SUSing: SU-net for Singing Voice Synthesis
- Blog: A3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing
- Blog: Multi-instrument Music Synthesis with Spectrogram Diffusion
- Blog: A Neural Vocoder with Hierarchical Generation of Amplitude and Phase Spectra for Statistical Parametric Speech Synthesis
- Blog: Mask-Weighted Spatial Likelihood Coding for Speaker-Independent Joint Localization and Mask Estimation
- Blog: Adversarially Trained Multi-Singer Sequence-to-Sequence Singing Synthesizer
- Blog: Adversarially Trained End-to-End Korean Singing Voice Synthesis System
- Blog: A Spectral Conversion Approach to Single-Channel Speech Enhancement
History & citation
Current · Permanent link
- This direction split from High Frequency Harmonic Reconstruction for Neural Audio (100% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_spectral_over_smoothing_350d4164,
title = {spectral over-smoothing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/spectral-over-smoothing/rdr_350d4164fbf6457f823e03e105149f36},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_spectral_over_smoothing_350d4164_v1,
title = {spectral over-smoothing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/spectral-over-smoothing/rdr_350d4164fbf6457f823e03e105149f36/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}