Image de couverture de livre

CosyEdit2: Speech-Editing-Oriented Reinforcement Learning Unlocks Better Zero-Shot TTS

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Junyang, Jia, Yuhang, Wang, Hui, Zhou, Jiaming, Gan, Yongchang, Qin, Yong
Format:	Preprint
Publié:	2026
Sujets:	Sound
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CosyEdit: Unlocking End-to-End Speech Editing Capability from Zero-Shot Text-to-Speech Models
par: Chen, Junyang, et autres
Publié: (2026)

Zero- and One-Shot Data Augmentation for Sentence-Level Dysarthric Speech Recognition in Constrained Scenarios
par: Wang, Shiyao, et autres
Publié: (2025)

LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling
par: Fan, Xiaoyu, et autres
Publié: (2026)

Speak, Edit, Repeat: High-Fidelity Voice Editing and Zero-Shot TTS with Cross-Attentive Mamba
par: Mohammad, Baher, et autres
Publié: (2025)

Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
par: Jiang, Ziyue, et autres
Publié: (2023)

SynTTS-Commands: A Public Dataset for On-Device KWS via TTS-Synthesized Multilingual Speech
par: Gan, Lu, et autres
Publié: (2025)

AudioEval: Automatic Dual-Perspective and Multi-Dimensional Evaluation of Text-to-Audio-Generation
par: Wang, Hui, et autres
Publié: (2025)

Iterate to Differentiate: Enhancing Discriminability and Reliability in Zero-Shot TTS Evaluation
par: Shen, Shengfan, et autres
Publié: (2026)

HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
par: Wang, Chunhui, et autres
Publié: (2024)

SeamlessEdit: Background Noise Aware Zero-Shot Speech Editing with in-Context Enhancement
par: Chen, Kuan-Yu, et autres
Publié: (2025)

GLAD: Global-Local Aware Dynamic Mixture-of-Experts for Multi-Talker ASR
par: Guo, Yujie, et autres
Publié: (2025)

IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
par: Deng, Wei, et autres
Publié: (2025)

TTA-Bench: A Comprehensive Benchmark for Evaluating Text-to-Audio Models
par: Wang, Hui, et autres
Publié: (2025)

ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis
par: Li, Haitao, et autres
Publié: (2026)

Towards Automatic Evaluation and High-Quality Pseudo-Parallel Dataset Construction for Audio Editing: A Human-in-the-Loop Method
par: Jia, Yuhang, et autres
Publié: (2025)

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech
par: Kim, Jaehyeon, et autres
Publié: (2024)

EME-TTS: Unlocking the Emphasis and Emotion Link in Speech Synthesis
par: Li, Haoxun, et autres
Publié: (2025)

E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
par: Eskimez, Sefik Emre, et autres
Publié: (2024)

MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis
par: Jiang, Ziyue, et autres
Publié: (2025)

Intelli-Z: Toward Intelligible Zero-Shot TTS
par: Jung, Sunghee, et autres
Publié: (2024)

GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor
par: Lee, Seokgi, et autres
Publié: (2025)

Interpretable Audio Editing Evaluation via Chain-of-Thought Difference-Commonality Reasoning with Multimodal LLMs
par: Jia, Yuhang, et autres
Publié: (2025)

FlexiVoice: Enabling Flexible Style Control in Zero-Shot TTS with Natural Language Instructions
par: Chen, Dekun, et autres
Publié: (2026)

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
par: Du, Zhihao, et autres
Publié: (2024)

SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation
par: Wang, Hui, et autres
Publié: (2025)

CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
par: Du, Zhihao, et autres
Publié: (2025)

MPE-TTS: Customized Emotion Zero-Shot Text-To-Speech Using Multi-Modal Prompt
par: Wu, Zhichao, et autres
Publié: (2025)

DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency
par: Chen, Yang, et autres
Publié: (2024)

DisCo-Speech: Controllable Zero-Shot Speech Generation with A Disentangled Speech Codec
par: Li, Tao, et autres
Publié: (2025)

Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model
par: Lehečka, Jan, et autres
Publié: (2024)

VoiceShop: A Unified Speech-to-Speech Framework for Identity-Preserving Zero-Shot Voice Editing
par: Anastassiou, Philip, et autres
Publié: (2024)

EMORL-TTS: Reinforcement Learning for Fine-Grained Emotion Control in LLM-based TTS
par: Li, Haoxun, et autres
Publié: (2025)

WildElder: A Chinese Elderly Speech Dataset from the Wild with Fine-Grained Manual Annotations
par: Wang, Hui, et autres
Publié: (2025)

IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
par: Zhou, Siyi, et autres
Publié: (2025)

Improving Zero-Shot Chinese-English Code-Switching ASR with kNN-CTC and Gated Monolingual Datastores
par: Zhou, Jiaming, et autres
Publié: (2024)

SonoEdit: Null-Space Constrained Knowledge Editing for Pronunciation Correction in LLM-Based TTS
par: Singh, Ayush Pratap, et autres
Publié: (2026)

Voice Impression Control in Zero-Shot TTS
par: Fujita, Kenichi, et autres
Publié: (2025)

AudioEditor: A Training-Free Diffusion-Based Audio Editing Framework
par: Jia, Yuhang, et autres
Publié: (2024)

Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations
par: Jeon, Yejin, et autres
Publié: (2024)

SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
par: Zhang, Hanlin, et autres
Publié: (2026)