CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space
cs.SD, cs.AI
Submitted: 2026-03-02
Updated: 2026-10-11
Comments: 7 pages, 7 figures
Code: https://github.com/YannickJadoul/Parselmouth
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectra
- VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration
- NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
- Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement
- FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching
- UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching
- Conformer: Convolution-augmented Transformer for Speech Recognition
- A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS
- LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
- NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs