CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
cs.SD, cs.AI, cs.CL
Submitted: 2026-08-09
Updated: 2026-08-26
Comments: 20 pages, 6 figures, 10 tables. Technical report
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MELA-TTS: Joint transformer-diffusion model with representation alignment for speech synthesis
- Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
- 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
- CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
- Mean Flows for One-step Generative Modeling
- MOSS-TTS Technical Report
- Classifier-Free Diffusion Guidance
- Qwen3-TTS Technical Report
- High-Fidelity Audio Compression with Improved RVQGAN
- Matcha-TTS: A fast TTS architecture with conditional flow matching
- Semantic-VAE: Semantic-Alignment Latent Representation for Better Speech Synthesis
- VibeVoice Technical Report
- Continuous Audio Language Models
- Multimodal Latent Language Modeling with Next-Token Diffusion
- Speech Synthesis From Continuous Features Using Per-Token Latent Diffusion
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching
- IntMeanFlow: Few-step Speech Generation with Integral Velocity Distillation
- CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis
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
- Harmonic Representations in Symbolic Music Transformers are Localized and Controllable
- 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