PHAST-Net: Attention-Guided, Physics-Informed Network for Estimation of Ideal Time-Frequency Representations

arXiv:2606.23665 · eess.AS, cs.CV · Submitted 2026-06-22 · Read on arXiv

eess.AS, cs.CV

Submitted: 2026-06-22

Updated: 2026-10-16

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Wavelet Transform — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Continuous Log-frequency Adaptive Wavelet Transform — 1× in this paper
• Sparsity — 1× in this paper · explained in 4 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• RIFT: Entropy-Optimised Fractional Wavelet Constellations for Ideal Time-Frequency Estimation
• Robust Time-Frequency Reconstruction by Learning Structured Sparsity

Related papers

• Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
• X-VC: Zero-shot Streaming Voice Conversion in Codec Space
• Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
• LiveAnon: Improving Privacy and Utility in Streaming Speaker Anonymization with Codec Language Models
• EarLog: Opportunistic Ear Physiology Sensing toward Personalized Hearing Risk Awareness
• VM-ARRAYDPS: Virtual Microphone Augmented Diffusion Posterior Sampling for Unsupervised Blind Speech Separation