{"total":75,"rows":[{"id":"2406.11768","title":"GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities","created":"2024-06-17","cited_by_count":156,"area":"lr"},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"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":"2501.15417","title":"AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement","created":"2025-01-26","cited_by_count":23,"area":null},{"id":"2110.07313","title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","created":"2021-10-14","cited_by_count":22,"area":null},{"id":"2211.02250","title":"Real-Time Target Sound Extraction","created":"2022-11-04","cited_by_count":22,"area":null},{"id":"2105.12395","title":"Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks","created":"2021-05-26","cited_by_count":17,"area":null},{"id":"2310.04567","title":"DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction","created":"2023-10-06","cited_by_count":12,"area":"diffusion"},{"id":"2409.09213","title":"ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds","created":"2024-09-13","cited_by_count":12,"area":null},{"id":"2103.13620","title":"SubSpectral Normalization for Neural Audio Data Processing","created":"2021-03-25","cited_by_count":11,"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":"2311.00320","title":"Semantic Hearing: Programming Acoustic Scenes with Binaural Hearables","created":"2023-11-01","cited_by_count":11,"area":null},{"id":"2409.08425","title":"SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer","created":"2024-09-12","cited_by_count":11,"area":"diffusion"},{"id":"2206.06126","title":"Robust Time Series Denoising with Learnable Wavelet Packet Transform","created":"2022-06-13","cited_by_count":10,"area":null},{"id":"2105.02702","title":"MIMII DUE: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection with Domain Shifts due to Changes in Operational and Environmental Conditions","created":"2021-05-06","cited_by_count":9,"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":"2104.13620","title":"IDMT-Traffic: An Open Benchmark Dataset for Acoustic Traffic Monitoring Research","created":"2021-04-28","cited_by_count":8,"area":null},{"id":"2205.07390","title":"Learning Representations for New Sound Classes With Continual Self-Supervised Learning","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2211.02448","title":"NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTS","created":"2022-11-04","cited_by_count":8,"area":"diffusion"},{"id":"2110.08895","title":"DECAR: Deep Clustering for learning general-purpose Audio Representations","created":"2021-10-17","cited_by_count":7,"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":"2408.13161","title":"Say No to Freeloader: Protecting Intellectual Property of Your Deep Model","created":"2024-08-23","cited_by_count":7,"area":null},{"id":"2102.07820","title":"Anomalous Sound Detection with Machine Learning: A Systematic Review","created":"2021-02-15","cited_by_count":5,"area":null},{"id":"2201.03386","title":"Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks","created":"2022-01-10","cited_by_count":5,"area":null},{"id":"2304.02319","title":"Efficient CNNs via Passive Filter Pruning","created":"2023-04-05","cited_by_count":5,"area":null},{"id":"2104.02523","title":"An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network","created":"2021-04-05","cited_by_count":4,"area":null},{"id":"2106.06858","title":"Improving weakly supervised sound event detection with self-supervised auxiliary tasks","created":"2021-06-12","cited_by_count":4,"area":null},{"id":"2107.01461","title":"A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification","created":"2021-07-03","cited_by_count":4,"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":"2211.01519","title":"SLICER: Learning universal audio representations using low-resource self-supervised pre-training","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2305.14546","title":"On the Transferability of Whisper-based Representations for \"In-the-Wild\" Cross-Task Downstream Speech Applications","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2409.04803","title":"Cross-attention Inspired Selective State Space Models for Target Sound Extraction","created":"2024-09-07","cited_by_count":4,"area":"ssm"},{"id":"2509.25275","title":"VoiceBridge: General Speech Restoration with One-step Latent Bridge Models","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2510.20441","title":"UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement","created":"2025-10-23","cited_by_count":4,"area":null},{"id":"2211.01515","title":"MAST: Multiscale Audio Spectrogram Transformers","created":"2022-11-02","cited_by_count":3,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2305.12712","title":"LEAN: Light and Efficient Audio Classification Network","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2102.11771","title":"Improving Deep Learning Sound Events Classifiers using Gram Matrix Feature-wise Correlations","created":"2021-02-23","cited_by_count":2,"area":null},{"id":"2105.11856","title":"Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices","created":"2021-05-25","cited_by_count":2,"area":null},{"id":"2110.08598","title":"A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer","created":"2021-10-16","cited_by_count":2,"area":null},{"id":"2210.17416","title":"Efficient Similarity-based Passive Filter Pruning for Compressing CNNs","created":"2022-10-27","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":"2506.04376","title":"Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2510.02187","title":"High-Fidelity Speech Enhancement via Discrete Audio Tokens","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2104.07213","title":"Attentive max feature map and joint training for acoustic scene classification","created":"2021-04-15","cited_by_count":1,"area":null},{"id":"2106.11335","title":"Do sound event representations generalize to other audio tasks? A case study in audio transfer learning","created":"2021-06-21","cited_by_count":1,"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":"2204.00218","title":"End-to-End Multi-speaker ASR with Independent Vector Analysis","created":"2022-04-01","cited_by_count":1,"area":null},{"id":"2210.08610","title":"Robust, General, and Low Complexity Acoustic Scene Classification Systems and An Effective Visualization for Presenting a Sound Scene Context","created":"2022-10-16","cited_by_count":1,"area":null},{"id":"2212.11277","title":"Audio Denoising for Robust Audio Fingerprinting","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2312.14005","title":"On the choice of the optimal temporal support for audio classification with Pre-trained embeddings","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2504.15214","title":"Histogram-based Parameter-efficient Tuning for Passive and Active Sonar Classification","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2509.18603","title":"SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and Effective Sample Filtering","created":"2025-09-23","cited_by_count":1,"area":"diffusion"},{"id":"2607.05251","title":"Privacy-Preserving Robustness Verification for Neural Networks","created":"2026-07-06","cited_by_count":1,"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":"2108.05008","title":"Robust Feature Learning on Long-Duration Sounds for Acoustic Scene Classification","created":"2021-08-11","cited_by_count":0,"area":null},{"id":"2203.04114","title":"A study on joint modeling and data augmentation of multi-modalities for audio-visual scene classification","created":"2022-03-07","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":"2206.08007","title":"DCASE 2022: Comparative Analysis Of CNNs For Acoustic Scene Classification Under Low-Complexity Considerations","created":"2022-06-16","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":"2303.05668","title":"UNFUSED: UNsupervised Finetuning Using SElf supervised Distillation","created":"2023-03-10","cited_by_count":0,"area":"distill"},{"id":"2306.11764","title":"On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2310.13388","title":"Music Augmentation and Denoising For Peak-Based Audio Fingerprinting","created":"2023-10-20","cited_by_count":0,"area":null},{"id":"2403.14246","title":"CATSE: A Context-Aware Framework for Causal Target Sound Extraction","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2409.11439","title":"Machine listening in a neonatal intensive care unit","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2410.16177","title":"A Framework for Evaluating Predictive Models Using Synthetic Image Covariates and Longitudinal Data","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2412.00312","title":"Raw Audio Classification with Cosine Convolutional Neural Network (CosCovNN)","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2412.03771","title":"A Benchmark of Generative Methods for Zero-Shot Environmental Sound Classification","created":"2024-12-04","cited_by_count":0,"area":"diffusion"},{"id":"2503.16862","title":"Improving Acoustic Scene Classification with City Features","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2509.02622","title":"IS${}^3$ : Generic Impulsive--Stationary Sound Separation in Acoustic Scenes using Deep Filtering","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2606.04844","title":"Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification","created":"2026-06-03","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":"2608.15037","title":"Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.21664","title":"Multi-Domain Clustering via Measure Quantization","created":"2026-09-18","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}