Distill Locally, Schedule Globally: Flow Maps for Few-Step Text-to-Speech
cs.SD, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
- Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
- Flow map matching with stochastic interpolants: A mathematical framework for consistency models
- Align Your Flow: Scaling Continuous-Time Flow Map Distillation
- How to build a consistency model: Learning flow maps via self-distillation
- SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
- IntMeanFlow: Few-step Speech Generation with Integral Velocity Distillation
- DSFlow: Dual Supervision and Step-Aware Architecture for One-Step Flow Matching Speech Synthesis
- One Step Diffusion via Shortcut Models
- On the Trajectory Regularity of ODE-based Diffusion Sampling
- Optimal Stepsize for Diffusion Sampling
- DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis
- Classifier-Free Diffusion Guidance
- Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation
- LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
- Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
- Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
- Robust Speech Recognition via Large-Scale Weak Supervision
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
- UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
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