Guidance at Pure Noise Erodes Speaker Similarity in Few-Step Token-Conditioned Flow-Matching TTS
cs.SD, cs.AI
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/16jhlee/FSU
Terminology
Sources
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- GLM-TTS Technical Report
- Mean Flows for One-step Generative Modeling
- dots.tts Technical Report
- FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation
- IntMeanFlow: Few-step Speech Generation with Integral Velocity Distillation
- CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
- Classifier-Free Guidance is a Predictor-Corrector
- Selective Classifier-free Guidance for Zero-shot Text-to-speech
- Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS
- How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models
- Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance
- CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
- Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
- MUSAN: A Music, Speech, and Noise Corpus
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