No article text was recorded for this version.
adversarial spectral refinement
Version 1 of 1179 papers241 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Fine-Tuning of Pre-Trained End-to-End Speech Recognition with Generative Adversarial Networks
- Blog: GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis
- Blog: Adversarial Permutation Invariant Training for Universal Sound Separation
- Blog: Improving Speech Intelligibility Through Speaker Dependent and Independent Spectral Style Conversion
- Blog: Effectiveness of Generative Adversarial Network for Non-Audible Murmur-to-Whisper Speech Conversion
- Blog: Adversarial joint training with self-attention mechanism for robust end-to-end speech recognition
- Blog: DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
- Blog: VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019
- Blog: PauseSpeech: Natural Speech Synthesis via Pre-trained Language Model and Pause-Based Prosody Modeling
- Blog: Improving Speech Recognition Using GAN-Based Speech Synthesis and Contrastive Unspoken Text Selection
- Blog: VSEGAN: Visual Speech Enhancement Generative Adversarial Network
- Blog: The USTC System for Blizzard Challenge 2017
- Blog: Recognition-Synthesis Based Non-Parallel Voice Conversion with Adversarial Learning
- Blog: Code-Switching Sentence Generation by Bert and Generative Adversarial Networks
- Blog: Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition
- Blog: Jointly Adversarial Enhancement Training for Robust End-to-End Speech Recognition
- Blog: Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
- Blog: Voice Conversion from Unaligned Corpora Using Variational Autoencoding Wasserstein Generative Adversarial Networks
- Blog: Emotional Voice Conversion With Cycle-consistent Adversarial Network
- Blog: Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation
- Blog: FlashSpeech: Efficient Zero-Shot Speech Synthesis
- Blog: SpeechPainter: Text-conditioned Speech Inpainting
- Blog: A Deformable Convolution GAN Approach for Speech Dereverberation in Cochlear Implant Users
- Blog: Continuous Emotional Intensity Controllable Speech Synthesis using Semi-supervised Learning
- Blog: Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks
- Blog: Adversarial Feature-Mapping for Speech Enhancement
- Blog: Generative Adversarial Network Based Acoustic Echo Cancellation
- Blog: StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
- Blog: Hierarchical and Multi-Scale Variational Autoencoder for Diverse and Natural Non-Autoregressive Text-to-Speech
- Blog: MeanVC: Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows
- Blog: VQVAE Unsupervised Unit Discovery and Multi-Scale Code2Spec Inverter for Zerospeech Challenge 2019
- Blog: PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS
- Blog: Speech Dereverberation Using Fully Convolutional Networks
- Blog: StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
- Blog: A Neural Vocoder with Hierarchical Generation of Amplitude and Phase Spectra for Statistical Parametric Speech Synthesis
- Blog: Permutation Invariant Training of Generative Adversarial Network for Monaural Speech Separation
- Blog: Generative Adversarial Network based Speaker Adaptation for High Fidelity WaveNet Vocoder
- Blog: RephraseTTS: Dynamic Length Text based Speech Insertion with Speaker Style Transfer
- Blog: Single-channel Speech Dereverberation via Generative Adversarial Training
- Blog: DDD: A Perceptually Superior Low-Response-Time DNN-based Declipper
- Blog: Increasing the Intelligibility and Naturalness of Alaryngeal Speech Using Voice Conversion and Synthetic Fundamental Frequency
- Blog: MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling
- Blog: Recognition-Synthesis Based Non-Parallel Voice Conversion with Adversarial Learning
- Blog: Generative Adversarial Network-Based Postfilter for STFT Spectrograms
- Blog: PauseSpeech: Natural Speech Synthesis via Pre-trained Language Model and Pause-based Prosody Modeling
- Blog: Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
- Blog: Adversarially Trained End-to-End Korean Singing Voice Synthesis System
- Blog: UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-Noise Ratio Condition
- Blog: Efficient and Stable Adversarial Learning Using Unpaired Data for Unsupervised Multichannel Speech Separation
- Blog: Universal Score-based Speech Enhancement with High Content Preservation
- Blog: Acoustic Modeling Using Adversarially Trained Variational Recurrent Neural Network for Speech Synthesis
- Blog: Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
- Blog: Investigating Generative Adversarial Networks Based Speech Dereverberation for Robust Speech Recognition
- Blog: Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech
- Blog: Music Separation Enhancement with Generative Modeling
- Blog: High Fidelity Speech Regeneration with Application to Speech Enhancement
- Blog: Toward Complex-Valued Neural Networks for Waveform Generation
- Blog: Timbre-Reserved Adversarial Attack in Speaker Identification
- Blog: A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS
- Blog: Leveraging Symmetrical Convolutional Transformer Networks for Speech to Singing Voice Style Transfer
Showing 60 of 179 papers.
History & citation
Current · Permanent link
- Adversarial Training to Prevent Over-smoothing in Speech Synthesis merged into this direction (64% overlap)
- Adversarial Refinement for High Fidelity Audio Synthesis merged into this direction (76% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_adversarial_spectral_refinement_bd8e32e2,
title = {adversarial spectral refinement},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/adversarial-spectral-refinement/rdr_bd8e32e24d084c318c61e7084f226556},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_adversarial_spectral_refinement_bd8e32e2_v1,
title = {adversarial spectral refinement},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/adversarial-spectral-refinement/rdr_bd8e32e24d084c318c61e7084f226556/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}