arXiv eess.AS

Audio and Speech Processing daily digest.

30 past editions, oldest first by date. Atom feed → · all categories

01 — Past editions

most recent first

2026-07-16 Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for... 4 papers · No. 55
2026-07-15 The Sound of Absence: Audio-Language Embedding Models Struggle with Negation 1 papers · No. 54
2026-07-13 Phone Segmentation and Recognition through Phonological Activation Mapping 1 papers · No. 52
2026-07-12 On the Role of Conversational Timing in Synthetic Training Data for ASR 1 papers · No. 51
2026-07-11 On the Role of Conversational Timing in Synthetic Training Data for ASR 1 papers · No. 50
2026-07-10 On the Role of Conversational Timing in Synthetic Training Data for ASR 1 papers · No. 49
2026-07-08 TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio... 1 papers · No. 47
2026-07-07 ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker... 1 papers · No. 46
2026-07-06 An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding... 1 papers · No. 45
2026-07-05 An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding... 1 papers · No. 44
2026-07-04 An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding... 1 papers · No. 43
2026-07-03 An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding... 1 papers · No. 42
2026-07-01 Is Natural Always Appropriate? Investigating Naturalness and Appropriateness... 2 papers · No. 40
2026-06-30 Semi-Supervised Sound Event Detection with Conditional Mixup and... 1 papers · No. 39
2026-06-25 SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness... 4 papers · No. 34
2026-06-24 Breaking Shortcut Learning for Cross-Trial EEG-Guided Target Speech... 2 papers · No. 33
2026-06-23 Domain-incremental audio classification using domain-specific experts and... 1 papers · No. 32
2026-06-22 Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation 4 papers · No. 31
2026-06-21 Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation 4 papers · No. 30
2026-06-20 Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation 4 papers · No. 29
2026-06-19 Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation 4 papers · No. 28
2026-06-18 Augmenting Dysarthric Speech Severity Assessment with MOS Supervision 1 papers · No. 27
2026-06-14 Adaptive Turn-Taking for Real-time Multi-Party Voice Agents 1 papers · No. 23
2026-06-13 Adaptive Turn-Taking for Real-time Multi-Party Voice Agents 1 papers · No. 22
2026-06-12 Adaptive Turn-Taking for Real-time Multi-Party Voice Agents 1 papers · No. 21
2026-06-11 Fast Speech Foundation Model Distillation Using Interleaved Stacking 1 papers · No. 20
2026-06-10 Optimizing 2D Input Representations and Sub-phase Fusion Strategies for... 2 papers · No. 19
2026-06-09 MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation 1 papers · No. 18
2026-06-08 SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large... 2 papers · No. 17
2026-05-30 Mitigating Stethoscope-Induced Shortcuts in Respiratory Sound Classification... 1 papers · No. 12

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.