Copertina

Robust TTS Training via Self-Purifying Flow Matching for the WildSpoof 2026 TTS Track

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yi, June Young, Kim, Hyeongju, Lee, Juheon
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Sound Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Training Flow Matching Models with Reliable Labels via Self-Purification
di: Kim, Hyeongju, et al.
Pubblicazione: (2025)

WildSpoof Challenge Evaluation Plan
di: Wu, Yihan, et al.
Pubblicazione: (2025)

DFKI-Speech System for WildSpoof Challenge: A robust framework for SASV In-the-Wild
di: Das, Arnab, et al.
Pubblicazione: (2026)

Length-Aware Rotary Position Embedding for Text-Speech Alignment
di: Kim, Hyeongju, et al.
Pubblicazione: (2025)

Flamed-TTS: Flow Matching Attention-Free Models for Efficient Generating and Dynamic Pacing Zero-shot Text-to-Speech
di: Huynh-Nguyen, Hieu-Nghia, et al.
Pubblicazione: (2025)

SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech System
di: Kim, Hyeongju, et al.
Pubblicazione: (2025)

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching
di: Yang, Jinhyeok, et al.
Pubblicazione: (2026)

IndexTTS 2.5 Technical Report
di: Li, Yunpei, et al.
Pubblicazione: (2026)

MOSS-TTS Technical Report
di: Gong, Yitian, et al.
Pubblicazione: (2026)

AutoStyle-TTS: Retrieval-Augmented Generation based Automatic Style Matching Text-to-Speech Synthesis
di: Luo, Dan, et al.
Pubblicazione: (2025)

UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information
di: Wang, Rui, et al.
Pubblicazione: (2025)

A2TTS: TTS for Low Resource Indian Languages
di: Bhadoriya, Ayush Singh, et al.
Pubblicazione: (2025)

Natural Yet Challenging to Detect: Robust In-the-Wild TTS through EMA and Dual-Scoring Prompt Selection -- Submission for WildSpoof 2026 TTS Track
di: Sun, Renhe, et al.
Pubblicazione: (2026)

DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech
di: Cho, Deok-Hyeon, et al.
Pubblicazione: (2025)

RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS
di: Wang, Cong, et al.
Pubblicazione: (2025)

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis
di: Choi, Youngwon, et al.
Pubblicazione: (2026)

Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting
di: Han, Wooseok, et al.
Pubblicazione: (2024)

A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data
di: Chou, Cheng-Kang, et al.
Pubblicazione: (2025)

Spotlight-TTS: Spotlighting the Style via Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
di: Kim, Nam-Gyu, et al.
Pubblicazione: (2025)

On the Effectiveness of Acoustic BPE in Decoder-Only TTS
di: Li, Bohan, et al.
Pubblicazione: (2024)

Towards Lightweight and Stable Zero-shot TTS with Self-distilled Representation Disentanglement
di: Chen, Qianniu, et al.
Pubblicazione: (2025)

Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE
di: Lian, Jiachen, et al.
Pubblicazione: (2022)

EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech
di: Cho, Deok-Hyeon, et al.
Pubblicazione: (2024)

Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input
di: Liu, Changsong, et al.
Pubblicazione: (2026)

PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion
di: Pankov, Vikentii, et al.
Pubblicazione: (2026)

EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation Steering
di: Xie, Tianxin, et al.
Pubblicazione: (2025)

Differentiable Reward Optimization for LLM based TTS system
di: Gao, Changfeng, et al.
Pubblicazione: (2025)

A Non-autoregressive Model for Joint STT and TTS
di: Sunder, Vishal, et al.
Pubblicazione: (2025)

Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models
di: Lee, Kyowoon, et al.
Pubblicazione: (2025)

TTS-1 Technical Report
di: Atamanenko, Oleg, et al.
Pubblicazione: (2025)

When Fine-Tuning Fails and when it Generalises: Role of Data Diversity and Mixed Training in LLM-based TTS
di: Purwar, Anupam, et al.
Pubblicazione: (2026)

Explore the Reinforcement Learning for the LLM based ASR and TTS system
di: Gao, Changfeng, et al.
Pubblicazione: (2025)

LoRP-TTS: Low-Rank Personalized Text-To-Speech
di: Bondaruk, Łukasz, et al.
Pubblicazione: (2025)

No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTS
di: Shin, Seungyoun, et al.
Pubblicazione: (2025)

Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNets
di: Liu, Chenlin, et al.
Pubblicazione: (2025)

SpoofCeleb: Speech Deepfake Detection and SASV In The Wild
di: Jung, Jee-weon, et al.
Pubblicazione: (2024)

Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation
di: Yang, Tianle, et al.
Pubblicazione: (2026)

CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment
di: Liu, Hanwen, et al.
Pubblicazione: (2026)

Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS
di: Seo, Deokjin, et al.
Pubblicazione: (2026)

DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech
di: Qi, Xin, et al.
Pubblicazione: (2024)