{"total":44,"rows":[{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176,"area":null},{"id":"2407.04051","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","created":"2024-07-04","cited_by_count":122,"area":null},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35,"area":null},{"id":"2204.09273","title":"Sound-Guided Semantic Video Generation","created":"2022-04-20","cited_by_count":35,"area":null},{"id":"2110.04176","title":"PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions","created":"2021-10-08","cited_by_count":26,"area":null},{"id":"2205.05949","title":"Automated Audio Captioning: An Overview of Recent Progress and New Challenges","created":"2022-05-12","cited_by_count":23,"area":null},{"id":"2305.17993","title":"Multi-Scale Attention for Audio Question Answering","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2508.15407","title":"When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models","created":"2025-08-21","cited_by_count":13,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2210.00943","title":"Simple Pooling Front-ends For Efficient Audio Classification","created":"2022-10-03","cited_by_count":9,"area":null},{"id":"2507.16343","title":"Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2505.04419","title":"Recognizing Ornaments in Vocal Indian Art Music with Active Annotation","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2109.10252","title":"Audiomer: A Convolutional Transformer For Keyword Spotting","created":"2021-09-21","cited_by_count":4,"area":null},{"id":"2409.15672","title":"Language-based Audio Moment Retrieval","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2509.18606","title":"FlexSED: Towards Open-Vocabulary Sound Event Detection","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2207.07773","title":"Segment-level Metric Learning for Few-shot Bioacoustic Event Detection","created":"2022-07-15","cited_by_count":3,"area":null},{"id":"2211.09376","title":"Balanced Deep CCA for Bird Vocalization Detection","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2409.17656","title":"Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2508.01394","title":"Via Score to Performance: Efficient Human-Controllable Long Song Generation with Bar-Level Symbolic Notation","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2503.02422","title":"Aggregation Strategies for Efficient Annotation of Bioacoustic Sound Events Using Active Learning","created":"2025-03-04","cited_by_count":2,"area":null},{"id":"2403.20130","title":"Sound event localization and classification using WASN in Outdoor Environment","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2406.13579","title":"Automated Bioacoustic Monitoring for South African Bird Species on Unlabeled Data","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2501.03464","title":"LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2505.10198","title":"A multi-head deep fusion model for recognition of cattle foraging events using sound and movement signals","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2604.13715","title":"Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2608.29999","title":"TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2107.10471","title":"Improving Polyphonic Sound Event Detection on Multichannel Recordings with the S{\\o}rensen-Dice Coefficient Loss and Transfer Learning","created":"2021-07-22","cited_by_count":0,"area":null},{"id":"2111.01205","title":"Evaluating robustness of You Only Hear Once(YOHO) Algorithm on noisy audios in the VOICe Dataset","created":"2021-11-01","cited_by_count":0,"area":null},{"id":"2306.06036","title":"SNeL: A Structured Neuro-Symbolic Language for Entity-Based Multimodal Scene Understanding","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2309.01574","title":"Object-Size-Driven Design of Convolutional Neural Networks: Virtual Axle Detection based on Raw Data","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2405.18153","title":"A Data-Centric Framework for Machine Listening Projects: Addressing Large-Scale Data Acquisition and Labeling through Active Learning","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2409.06196","title":"MTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2409.11262","title":"The Sounds of Home: A Speech-Removed Residential Audio Dataset for Sound Event Detection","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2411.10729","title":"On-device Anomaly Detection in Conveyor Belt Operations","created":"2024-11-16","cited_by_count":0,"area":null},{"id":"2504.04428","title":"Formula-Supervised Sound Event Detection: Pre-Training Without Real Data","created":"2025-04-06","cited_by_count":0,"area":null},{"id":"2507.01563","title":"Real-Time Emergency Vehicle Siren Detection with Efficient CNNs on Embedded Hardware","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2602.06917","title":"Automatic Detection and Analysis of Singing Mistakes for Music Pedagogy","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.10623","title":"Geo-ATBench: A Benchmark for Geospatial Audio Tagging with Geospatial Semantic Context","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.14917","title":"Spectrogram features for audio and speech analysis","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2606.19568","title":"Exploring Feature Extraction Technique Parameters for Acoustic Gunshot Classification","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.13571","title":"Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.07893","title":"Explainable Temporal Attention-based Defect Detection For Fillet Joints in Real-Time Gas Metal Arc Welding Based on Multi-modal Data","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.15215","title":"Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal Perception","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}