TTS-Q: Perception-Guided Post-Training Quantization of Text-to-Speech Diffusion Transformers
cs.SD, cs.LG, eess.AS
Submitted: 2026-08-11
Updated: 2026-10-14
Terminology
Sources
- Seed-TTS: A Family of High-Quality Versatile Speech Generation Models
- E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
- Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
- BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
- Up or Down? Adaptive Rounding for Post-Training Quantization
- UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
- NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
- Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
- LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space
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