WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning
cs.SD, cs.AI, eess.AS, eess.SP
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/sh-lee-prml/WaveGen
Terminology
Sources
- Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
- Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
- WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling
- F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
- Moshi: a speech-text foundation model for real-time dialogue
- Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
- BareWave: Waveform-Native Flow-Matching Text-to-Speech
- MOSS-TTS Technical Report
- Qwen3-TTS Technical Report
- DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors
- Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization
- Back to Basics: Let Denoising Generative Models Denoise
- WaveNet: A Generative Model for Raw Audio
- VibeVoice Technical Report
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
- LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space
- UniAudio: An Audio Foundation Model Toward Universal Audio Generation
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- 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