An Interpretable, Controllable Time-Varying IIR Denoiser for On-Device Assistive Hearing

arXiv:2603.02794 · cs.SD, cs.AI, cs.LG, eess.AS · Submitted 2026-03-03 · Read on arXiv

cs.SD, cs.AI, cs.LG, eess.AS

Submitted: 2026-03-03

Updated: 2026-09-21

Comments: Accepted at SLT26 (IEEE Spoken Language Technology 2026)

Code: https://github.com/magenta/ddsp

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

Terminology

• Time-Varying Filtering — 4× in this paper
• Digital Signal Processing — 3× in this paper
• Fast-Weight Programmer — 3× in this paper
• 1D CNN — 2× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Differentiable Digital Signal Processing — 2× in this paper
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Time-Varying Biquad Cascade — 2× in this paper
• Ablation — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Decoupling — 1× in this paper · explained in 2 episodes
• Edge AI — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Gate Recurrent Unit — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Hearing-Aid Speech Quality Index — 1× in this paper
• Meta-learning — 1× in this paper · explained in 2 episodes
• Parameter Efficiency — 1× in this paper · explained in 3 episodes

Sources

• Improving Resource-Efficient Speech Enhancement via Neural Differentiable DSP Vocoder Refinement
• Accelerating Automatic Differentiation of Direct Form Digital Filters
• SAM Audio: Segment Anything in Audio
• High-Fidelity Noise Reduction with Differentiable Signal Processing
• Low bit rate binaural link for improved ultra low-latency low-complexity multichannel speech enhancement in Hearing Aids

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
• 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
• Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment