arXiv AI
AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 20
RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching
arXiv:2605. 22083v2 Announce Type: replace-cross Abstract: While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment.
arXiv Machine Learning
3d ago
Noise-Robust Forced Alignment for Spontaneous Speech
arXiv:2610.22583v1 Announce Type: new Abstract: We show that forced aligners degrade on spontaneous, noisy real-world speech, and that fillers, laughter, and disfluencies corrupt word boundaries, imp...
arXiv AI
Jul 24
AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching
arXiv:2603. 01006v3 Announce Type: replace-cross Abstract: REPresentation Alignment (REPA) improves the training of generative flow models by aligning intermediate hidden states with pretrained teacher features, but its effectiveness in token-conditioned audio Flow Matching critically depends on the choice of supervised layers, which is typically made heuristically based on the depth.
arXiv AI
Jun 9
BareWave: Waveform-Native Flow-Matching Text-to-Speech
arXiv:2606. 09048v1 Announce Type: cross Abstract: Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling.
arXiv Machine Learning
Aug 17
SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos
arXiv:2510. 02916v2 Announce Type: replace-cross Abstract: We propose SALSA-V, a multimodal video-to-audio generation model capable of synthesizing highly synchronized, high-fidelity long-form audio from silent video content.
arXiv Machine Learning
1d ago
MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning
arXiv:2610.27491v1 Announce Type: cross Abstract: Real-world audio typically contains concurrent sound events, yet standard self-supervised methods treat each clip as an isolated training unit withou...