{"total":25,"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":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54,"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":"2203.15751","title":"A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification","created":"2022-03-29","cited_by_count":11,"area":null},{"id":"2402.02694","title":"Description on IEEE ICME 2024 Grand Challenge: Semi-supervised Acoustic Scene Classification under Domain Shift","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2110.01506","title":"Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations","created":"2021-10-04","cited_by_count":4,"area":null},{"id":"2509.04166","title":"Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2211.02940","title":"Effective Audio Classification Network Based on Paired Inverse Pyramid Structure and Dense MLP Block","created":"2022-11-05","cited_by_count":3,"area":null},{"id":"2308.11923","title":"Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2501.09394","title":"Quantum-Enhanced Transformers for Robust Acoustic Scene Classification in IoT Environments","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2110.09598","title":"Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2106.07428","title":"Audio Attacks and Defenses against AED Systems -- A Practical Study","created":"2021-06-14","cited_by_count":0,"area":null},{"id":"2107.14658","title":"Task 1A DCASE 2021: Acoustic Scene Classification with mismatch-devices using squeeze-excitation technique and low-complexity constraint","created":"2021-07-30","cited_by_count":0,"area":null},{"id":"2112.13450","title":"Acoustic scene classification using auditory datasets","created":"2021-12-26","cited_by_count":0,"area":null},{"id":"2201.12352","title":"Automatic Audio Captioning using Attention weighted Event based Embeddings","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2204.00555","title":"1-D CNN based Acoustic Scene Classification via Reducing Layer-wise Dimensionality","created":"2022-03-31","cited_by_count":0,"area":null},{"id":"2204.11420","title":"Audio-Visual Scene Classification Using A Transfer Learning Based Joint Optimization Strategy","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2206.13476","title":"Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2310.13404","title":"Definition-independent Formalization of Soundscapes: Towards a Formal Methodology","created":"2023-10-20","cited_by_count":0,"area":null},{"id":"2503.16862","title":"Improving Acoustic Scene Classification with City Features","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2509.11168","title":"An Entropy-Guided Curriculum Learning Strategy for Data-Efficient Acoustic Scene Classification under Domain Shift","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2510.17345","title":"DDSC: Dynamic Dual-Signal Curriculum for Data-Efficient Acoustic Scene Classification under Domain Shift","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2606.20893","title":"Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.30784","title":"Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.34907","title":"SincDPNet: Interpretable Raw-Waveform Bathroom Activity Recognition for Assistive Living","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}