Acoustic Progress Propagation for Long-Horizon Speculative Decoding in ASR

arXiv:2609.33245 · eess.AS, cs.CL · Submitted 2026-09-27 · Read on arXiv

eess.AS, cs.CL

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/yuanyuanjia71-spec/ProgDraft

Terminology

• Alignment — 10× in this paper · explained in 1 episode
• Speculative Decoding — 9× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Verification — 4× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Block Diffusion — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Qwen3-ASR Technical Report
• Accelerating Large Language Model Decoding with Speculative Sampling
• Alignment Drift in Single-Model Speculative Decoding for ASR: Mechanism, Correction, and Cost

Related papers

• 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
• Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
• Towards Audio Token Compression in Large Audio Language Models
• WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detection
• ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions