AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation
cs.SD, cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Project page: https://alignaudio.github.io/AlignAudio
Terminology
Sources
- Zero-shot Voice Conversion with Diffusion Transformers
- UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities
- EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer
- MeanVC: Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows
- Flow-GRPO: Training Flow Matching Models via Online RL
- Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
- MUSAN: A Music, Speech, and Noise Corpus
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