{"total":18,"rows":[{"id":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","cited_by_count":11,"area":null},{"id":"2605.26176","title":"PitchBench: Measuring Pitch Hearing in Audio-Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.26968","title":"RedVox: Safety and Fairness Gaps in Speech Models Across Languages","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.04383","title":"Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.27109","title":"MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.27783","title":"SURE-Voice: A Front-End Baseline for Speech-Evidence Filtering in Speech LLMs","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.27817","title":"Auditing generative audio calls for known-task audio-llm evaluation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.32804","title":"Finding Emotions Where They Belong: Rethinking Audio Emotion Recognition through Masked Temporal Affective Grounding","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34030","title":"Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34806","title":"On Temporal Binding in Large Audio Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37317","title":"What Comes Next? Omni-StoryBench for Evaluating Story-Grounded Omnimodal Generation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38491","title":"Role-guided Speaker Deletion Verification in Clinical Psychiatry Speech Recordings with Audio Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.10208","title":"CARES: A Controlled Synthetic Benchmark of Speaker Reactions to Sound","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10663","title":"BEANS-Next and ROOTS: Broadening Audio-Language Capabilities for Bioacoustics","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11461","title":"Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13550","title":"Personalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear?","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16942","title":"UA-Bench: Benchmarking Large Audio-Language Models on Underwater Acoustic Recognition","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}