Cover Image

Training Flow Matching Models with Reliable Labels via Self-Purification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Hyeongju, Yu, Yechan, Yi, June Young, Lee, Juheon
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Artificial Intelligence Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

Improving Test-Time Performance of RVQ-based Neural Codecs
by: Kim, Hyeongju, et al.
Published: (2025)

Robust TTS Training via Self-Purifying Flow Matching for the WildSpoof 2026 TTS Track
by: Yi, June Young, et al.
Published: (2025)

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

DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance
by: Yang, Jinhyeok, et al.
Published: (2024)

Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detection
by: Ryu, Myeonghoon, et al.
Published: (2025)

Leveraging Contrastive Learning and Self-Training for Multimodal Emotion Recognition with Limited Labeled Samples
by: Fan, Qi, et al.
Published: (2024)

RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
by: Kim, June-Woo, et al.
Published: (2024)

MusicFlow: Cascaded Flow Matching for Text Guided Music Generation
by: Prajwal, K R, et al.
Published: (2024)

Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles
by: Toikkanen, Miika, et al.
Published: (2025)

Zero-Shot Voice Conversion via Content-Aware Timbre Ensemble and Conditional Flow Matching
by: Pan, Yu, et al.
Published: (2024)

BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models
by: Liang, Susan, et al.
Published: (2025)

GuitarFlow: Realistic Electric Guitar Synthesis From Tablatures via Flow Matching and Style Transfer
by: Loth, Jackson, et al.
Published: (2025)

BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classification
by: Kim, June-Woo, et al.
Published: (2024)

Mitigating Latent Mismatch in cVAE-Based Singing Voice Synthesis via Flow Matching
by: Yun, Minhyeok, et al.
Published: (2026)

DSA-Tokenizer: Disentangled Semantic-Acoustic Tokenization via Flow Matching-based Hierarchical Fusion
by: Zhang, Hanlin, et al.
Published: (2026)

Mitigating Stethoscope-Induced Shortcuts in Respiratory Sound Classification under Federated Domain Generalization with Causality-Inspired Interventions
by: Koo, Heejoon, et al.
Published: (2026)

Toward Efficient Speech Emotion Recognition via Spectral Learning and Attention
by: Lee, HyeYoung, et al.
Published: (2025)

Neural Speech Embeddings for Speech Synthesis Based on Deep Generative Networks
by: Lee, Seo-Hyun, et al.
Published: (2023)

UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching
by: Choi, Woongjib, et al.
Published: (2025)

Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis
by: Yang, Dong, et al.
Published: (2025)

Improved Intelligibility of Dysarthric Speech using Conditional Flow Matching
by: Das, Shoutrik, et al.
Published: (2025)

DiT-Flow: Speech Enhancement Robust to Multiple Distortions based on Flow Matching in Latent Space and Diffusion Transformers
by: Cao, Tianyu, et al.
Published: (2026)

Generalizable Prompt Tuning for Audio-Language Models via Semantic Expansion
by: Jang, Jaehyuk, et al.
Published: (2026)

CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching
by: Zhang, Leying, et al.
Published: (2025)

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

AHAMask: Reliable Task Specification for Large Audio Language Models without Instructions
by: Guo, Yiwei, et al.
Published: (2025)

OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching
by: Huynh-Nguyen, Hieu-Nghia, et al.
Published: (2025)

DSFlow: Dual Supervision and Step-Aware Architecture for One-Step Flow Matching Speech Synthesis
by: Lin, Bin, et al.
Published: (2026)

Reliability-Aware Geometric Fusion for Robust Audio-Visual Navigation
by: Liu, Teng, et al.
Published: (2026)

Leveraging Label Potential for Enhanced Multimodal Emotion Recognition
by: Shao, Xuechun, et al.
Published: (2025)

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

FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching
by: Yun, Jun-Hak, et al.
Published: (2025)

Super Monotonic Alignment Search
by: Lee, Junhyeok, et al.
Published: (2024)

Few-step Adversarial Schrödinger Bridge for Generative Speech Enhancement
by: Han, Seungu, et al.
Published: (2025)

Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization
by: Lee, Sang-Hoon, et al.
Published: (2024)

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

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

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