Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends

arXiv:2608.30326 · cs.SD, cs.AI · Submitted 2026-08-31 · Read on arXiv

cs.SD, cs.AI

Submitted: 2026-08-31

Updated: 2026-08-31

Terminology

• Learned Observation-Adding — 5× in this paper
• Benchmark — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Cross-Band Attention Mixer — 2× in this paper
• Generative AI — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Word Error Rate — 2× in this paper
• Adaptation — 1× in this paper · explained in 1 episode
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes

Sources

• A light-weight full-band speech enhancement model
• Adam: A Method for Stochastic Optimization

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