Zero-Shot TTS

TTS: Text-to-Speech

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 233% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 42

All topics

Beyond Token Revision: Investigating Mask-and-Replace Diffusion for Zero-Shot Text-to-Speech
Oct 7, 2026Hounsu Kim, Joonyong Park, Yuki Saito +2Zero-Shot TTS Audio Diffusion Models
KAIST, Republic of Korea · The University of Tokyo, Japan · National Institute of Advanced Industrial Science and Technology (AIST), Japan
BanglaBox: A Phonetically-Balanced Corpus and Data-Efficient Foundation-Model Adaptation for Bangla Text-to-Speech with Zero-Shot Voice Cloning
Oct 6, 2026Emtiaz Uddin Ahmed, Araf Mahmud, Sajib Hossain +3Text-to-Speech Low-Resource TTS Synthesis
A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment Models
Oct 5, 2026Yunus Emre Ozkose, Alperen Kahraman, Ali HaznedarogluTTS Synthesis TTS Evaluation
Sestek, Ankara, Türkiye
Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning
Sep 29, 2026Jian Chen, You Zhang, Mark VintonTTS Synthesis Zero-Shot TTS
Dolby Laboratories
RAWD-TTS: Ratio-Free Reward Alignment for Discrete-Diffusion Voice Cloning
Sep 29, 2026Maxim Maslov, Kirill Borodin, Vasilii Kudryavtsev +2Audio Diffusion Models Zero-Shot TTS
lab260, Yerevan, Armenia · BitmanagerAI, Dubai, UAE · MTUCI, Moscow, Russia
DEFINE: Exemplar-Guided Accent Control for Zero-Shot TTS
Sep 26, 2026Ambuj Mehrish, Abhinaba Roy, Alex Ivanov +2TTS Synthesis Zero-Shot TTS
Ca’ Foscari University of Venice · Singapore University of Technology and Design · Kandinsky Lab +1
EditVoice: Variable-Length Non-Autoregressive Zero-Shot TTS and Speech Editing with Edit Flows
Sep 24, 2026Hongyao Deng, Wenhao Guan, Xuetao Lin +4TTS Synthesis Speech Editing
School of Informatics, Xiamen University, China · School of Electronic Science and Engineering, Xiamen University, China
Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning
Sep 24, 2026Yoomee Cho, Jisun LeeTTS Synthesis Zero-Shot TTS
ESTsoft, Seoul, Republic of Korea
Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech
Sep 23, 2026Hyoeun Kim, Yujun Lee, Kyuhong ShimZero-Shot TTS Machine Unlearning
Sungkyunkwan University, Republic of Korea
TTS-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints
Sep 20, 2026Xubin Yue, Zhenhua Xu, Zhebo Wang +5Zero-Shot TTS
Zhejiang University · Binjiang Institute of Zhejiang University · Hangzhou International Innovation Institute, Beihang University +1
Cross-Lingual F5-TTS 2: A Simplified Framework for Language-Agnostic Voice Cloning
Sep 14, 2026Qingyu Liu, Rixi Xu, Yushen Chen +11TTS Synthesis Zero-Shot TTS
Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA · MoE Key Lab of Artificial Intelligence, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China +3
StepAudio 3 Gen Technical Report
Sep 14, 2026Bin Lin, Bo Zhao, Boyang Wang +68TTS Synthesis Zero-Shot TTS
Post-Training Zero-Shot TTS for Fine-Grained Emotion and Duration Control via Natural Language
Sep 10, 2026Lianru Gao, Yujie Guo, Yong QinTTS Synthesis Zero-Shot TTS
TMCC, College of Computer Science, Nankai University, Tianjin, China
Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization
Aug 12, 2026Peijie Chen, Zhuanling Zha, Zhipeng Nie +8Speech Processing Zero-Shot TTS
Didichuxing Co. Ltd
Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder
Aug 12, 2026Huaxuan Wang, Huimin Wang, Ruiyu Zhang +2TTS Synthesis Zero-Shot TTS
NetEase Youdao, Beijing, China
Luna-TTS Family Technical Report
Aug 12, 2026Feng Yin, Shuai Shi, Junjie Zheng +19Non-Autoregressive Text Generation TTS Synthesis
VUI Labs Research
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
Aug 9, 2026Yuqian Zhang, Yao Shi, Kexin Huang +6TTS Synthesis Streaming TTS Synthesis
Work done during internship at OPPO. · OPPO AI Center · Fudan University +1
CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis
Aug 8, 2026Zhisheng Zheng, Xiaohang Sun, Zhu Liu +5TTS Synthesis Zero-Shot TTS
The University of Texas at Austin · Amazon
SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation
Aug 7, 2026Hanke Xie, Haopeng Lin, Jiale Qian +13Zero-Shot TTS Autoregressive Generation
Soul AI Lab, China
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks
Aug 3, 2026Yu Zhang, Ruiqi Li, Changhao Pan +3Text-to-Audio Generation TTS Synthesis
1ByteDance · 2Zhejiang University
Zero-Shot Face-to-Speech Synthesis via Latent Space Adaptation of a Style-Diffusion TTS Model
Jul 29, 2026Carlos Muñoz-Romero, Jose A. Gonzalez-LopezTTS Synthesis Zero-Shot TTS
Universitat Oberta de Catalunya (UOC), Spain · Monoceros Labs, Spain · Dpt. of Signal Theory, Telematics and Communications, University of Granada, Spain
Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs
Jul 23, 2026Muyang Du, Shuang Yu, Junjie LaiTTS Synthesis Streaming TTS Synthesis
NVIDIA · Shanghai, China
Best-of- $N$ TTS Evaluation is Confounded by ASR Family Alignment
Jul 9, 2026Taehyung Yu, Seongjae KangSpeech Generation Evaluation TTS Evaluation
KAIST, Daejeon, South Korea.
GRAFT: Grafted Reference Audio for Fine-grained Pronunciation in Zero-shot Text-to-Speech
Jul 2, 2026Antonis Asonitis, Francesco Verdini, Aref Farhadipour +4TTS Synthesis Zero-Shot TTS
AGIGO · ETH Zurich · 1AGIGO 2ETH Zurich +4
VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation
Jun 25, 2026Tianxin Xie, Chenxing Li, Dong Yu +1Test-Time Adaptation Reinforcement Learning
The Hong Kong University of Science and Technology (Guangzhou) · Tencent
Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS
Jun 24, 2026Runwu Shi, Yujin Wang, Hongjin Song +8Flow Matching Classifier-Free Guidance
Institute of Science Tokyo · Wuhan University · Beijing Institute of Technology +1
Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis
Jun 24, 2026Lianbo Liu, Shiao Zhu, Kai Washizaki +10TTS Synthesis Data Augmentation
SB Intuitions
An Evaluation Framework for Text-to-Speech Voice Reconstruction
Jun 19, 2026Ariadna Sanchez, Christoph Minixhofer, Korin Richmond +3Speech Generation Evaluation TTS Evaluation
The Centre for Speech Technology Research, University of Edinburgh, UK
SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations
Jun 10, 2026Peijie Chen, Wenhao Guan, Weijie Wu +7Variational Autoencoders Audio Representation Learning
School of Informatics, Xiamen University, China · School of Electronic Science and Engineering, Xiamen University, China · DiDi Global Inc., Beijing, China
BareWave: Waveform-Native Flow-Matching Text-to-Speech
Jun 8, 2026Wei Fan, Chao-Hong Tan, Qian Chen +5Flow Matching TTS Synthesis
1Anhui Province Key Laboratory of Digital Security · 2Tongyi Fun Team, Alibaba Group

Oct 7, 2026, eess.ASJ/K move · Enter open · S save

Beyond Token Revision: Investigating Mask-and-Replace Diffusion for Zero-Shot Text-to-Speech

Hounsu Kim, Joonyong Park, Yuki Saito, Satoru Fukayama+1

KAIST, Republic of Korea · The University of Tokyo, Japan · National Institute of Advanced Industrial Science and Technology (AIST), Japan

Zero-Shot TTS Audio Diffusion Models Speech Language Models

Open paper AskPDF arXiv

Unlike autoregressive models, discrete diffusion-based models for zero-shot text-to-speech generate speech tokens in parallel and can revisit earlier predictions. Mask-and-replace training extends mask-only training by randomly replacing some tokens, and its gains are commonly attributed to self-correction, the ability to revise previously generated tokens. However, exposure to randomly perturbed context during training may itself improve generation, raising the question of whether these gains require inference-time token revision. To investigate this question, we use DeMaR, which combines mask-and-replace training with confidence-ranked mask-only sampling while preserving the total training corruption probability. Trained from scratch on LibriTTS, DeMaR achieves lower word error rates (WER) than autoregressive and mask-only diffusion baselines using the same speech tokenizer. This advantage persists when each token remains unchanged after first being unmasked. Matched training conditions on two heterogeneous speech tokenizers show that both noisy-context augmentation and replacement supervision improve WER under this restriction. These findings demonstrate training-side benefits of replacement beyond enabling inference-time token revision.

Momentum

Related topics

Latest papers 42