@article{bb387100,
AUTHOR = "Li, P. and Roch, M.A. and Klinck, H. and Fleishman, E. and Gillespie, D. and Nosal, E.M. and Shiu, Y. and Liu, X.B.",
TITLE = "Learning Stage-Wise GANs for Whistle Extraction in Time-Frequency
Spectrograms",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "9302-9314",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381164"}
@article{bb387101,
AUTHOR = "Madhu, A. and Suresh, K.",
TITLE = "RQNet: Residual Quaternion CNN for Performance Enhancement in Low
Complexity and Device Robust Acoustic Scene Classification",
JOURNAL = MultMed,
VOLUME = "25",
YEAR = "2023",
PAGES = "8780-8792",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381165"}
@article{bb387102,
AUTHOR = "Li, Y.X. and Cao, W. and Xie, W. and Li, J.L. and Benetos, E.",
TITLE = "Few-Shot Class-Incremental Audio Classification Using Dynamically
Expanded Classifier With Self-Attention Modified Prototypes",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "1346-1360",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381166"}
@article{bb387103,
AUTHOR = "Valimaki, V. and Prawda, K. and Schlecht, S.J.",
TITLE = "Two-Stage Attenuation Filter for Artificial Reverberation",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "391-395",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381167"}
@article{bb387104,
AUTHOR = "Jiang, P.X. and Yang, Y. and Zou, C.R. and Wang, Q.Y.",
TITLE = "An Attention-Based Time-Frequency Pyramid Pooling Strategy in Deep
Convolutional Networks for Acoustic Scene Classification",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "296-300",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381168"}
@article{bb387105,
AUTHOR = "Ooi, K. and Ong, Z.T. and Watcharasupat, K.N. and Lam, B. and Hong, J.Y. and Gan, W.S.",
TITLE = "ARAUS: A Large-Scale Dataset and Baseline Models of Affective
Responses to Augmented Urban Soundscapes",
JOURNAL = AffCom,
VOLUME = "15",
YEAR = "2024",
NUMBER = "1",
MONTH = "January",
PAGES = "105-120",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381169"}
@article{bb387106,
AUTHOR = "Gan, W.S. and Hong, J.Y. and Lam, B. and Watcharasupat, K.N. and Ong, Z.T. and Ooi, K.",
TITLE = "ARAUS: A Large-Scale Dataset and Baseline Models of Affective
Responses to Augmented Urban Soundscapes",
JOURNAL = AffCom,
VOLUME = "16",
YEAR = "2025",
NUMBER = "2",
MONTH = "April",
PAGES = "1260-1260",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381169"}
@article{bb387107,
AUTHOR = "Vielhaben, J. and Lapuschkin, S. and Montavon, G. and Samek, W.",
TITLE = "Explainable AI for time series via Virtual Inspection Layers",
JOURNAL = PR,
VOLUME = "150",
YEAR = "2024",
PAGES = "110309",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381170"}
@inproceedings{bb387108,
AUTHOR = "Li, X.M. and Li, X.R. and Gu, S.M. and Li, J.Y.",
TITLE = "A Cooperative Target Search and Rescue Guidance System Design Based
on Acoustic Spectrum Analysis",
BOOKTITLE = CVIDL23,
YEAR = "2023",
PAGES = "541-544",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381171"}
@article{bb387109,
AUTHOR = "Moliner, E. and Fierro, L. and Wright, A. and Hamalainen, M.S. and Valimaki, V.",
TITLE = "Noise Morphing for Audio Time Stretching",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1144-1148",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381172"}
@article{bb387110,
AUTHOR = "Haider, D. and Lostanlen, V. and Ehler, M. and Balazs, P.",
TITLE = "Instabilities in Convnets for Raw Audio",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1084-1088",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381173"}
@article{bb387111,
AUTHOR = "Huhtala, V. and Juvela, L. and Schlecht, S.J.",
TITLE = "KLANN: Linearising Long-Term Dynamics in Nonlinear Audio Effects
Using Koopman Networks",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1169-1173",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381174"}
@article{bb387112,
AUTHOR = "Lu, Z. and Wang, J. and Lian, J. and Wang, Y.M.",
TITLE = "A Mode-Matching Approach for Acoustic Vortex Generation in Circular
Array Configurations",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1590-1594",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381175"}
@article{bb387113,
AUTHOR = "Tsai, M.C.H. and Wu, H.C. and Huang, S.C.H. and Chang, S.Y.",
TITLE = "Novel Audio Mosaic Using LPC-Coefficient and Excitation-Codeword
Permutations",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "1690-1694",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381176"}
@article{bb387114,
AUTHOR = "Zhu, T. and Qian, G.B.",
TITLE = "Double Branches and Stages Neural Network for Joint Acoustic Echo and
Noise Suppression",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2150-2154",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381177"}
@article{bb387115,
AUTHOR = "Wang, F.J.R. and Abhayapala, T.D. and Zhang, J.H.A. and Samarasinghe, P.N.",
TITLE = "Reproducing the Acoustic Velocity Vectors in a Spherical Listening
Region",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2220-2224",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381178"}
@article{bb387116,
AUTHOR = "Schlecht, S.J. and Scerbo, M. and de Sena, E. and Valimaki, V.",
TITLE = "Modal Excitation in Feedback Delay Networks",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2690-2694",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381179"}
@article{bb387117,
AUTHOR = "Erol, M.H. and Senocak, A. and Feng, J. and Chung, J.S.",
TITLE = "Audio Mamba: Bidirectional State Space Model for Audio Representation
Learning",
JOURNAL = SPLetters,
VOLUME = "31",
YEAR = "2024",
PAGES = "2975-2979",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381180"}
@article{bb387118,
AUTHOR = "Sheng, M.J. and Miao, Y.C. and Li, Y.S. and Liu, C.S.",
TITLE = "Overlapping Whistle-and-Click Separation for Whale Signals",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "76-80",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381181"}
@article{bb387119,
AUTHOR = "Yoshinaga, T. and Tanaka, K. and Bando, Y. and Imoto, K. and Morishima, S.",
TITLE = "Onset-and-Offset-Aware Sound Event Detection via Differentiable
Frame-to-Event Mapping",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "186-190",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381182"}
@article{bb387120,
AUTHOR = "Xu, G.J. and Qu, K. and Li, Z.L. and Zhang, Z.X. and Xu, P. and Gao, D. and Dai, X.D.",
TITLE = "Enhanced Inversion of Sound Speed Profile Based on a Physics-Inspired
Self-Organizing Map",
JOURNAL = RS,
VOLUME = "17",
YEAR = "2025",
NUMBER = "1",
PAGES = "132",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381183"}
@article{bb387121,
AUTHOR = "Chen, L.W. and Zhou, X.R. and Chen, Q.J. and Xiong, F. and Chen, H.H.",
TITLE = "Investigating the Effective Dynamic Information of Spectral Shapes
for Audio Classification",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "1114-1126",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381184"}
@article{bb387122,
AUTHOR = "Yi, Q.L. and Xie, C.G. and Guan, D.H. and Yuan, W.W.",
TITLE = "Man2Marine: Marine mammal sound classification in small samples by
transfer learning from human sound data",
JOURNAL = PRL,
VOLUME = "190",
YEAR = "2025",
PAGES = "185-191",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381185"}
@article{bb387123,
AUTHOR = "Li, M.T. and Zhuang, T. and Chen, K. and Zhong, J.X. and Lu, J.",
TITLE = "Deep Learning-Based Approach for Identification and Compensation of
Nonlinear Distortions in Parametric Array Loudspeakers",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1455-1459",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381186"}
@article{bb387124,
AUTHOR = "Biernacki, P. and Libal, U.",
TITLE = "Nonlinear Schur-Type Audio Signal Parameterization for Convolutional
Networks",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1665-1669",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381187"}
@article{bb387125,
AUTHOR = "Jiang, X.H. and Ai, Y. and Zheng, R.C. and Ling, Z.H.",
TITLE = "A Streamable Neural Audio Codec With Residual Scalar-Vector
Quantization for Real-Time Communication",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "1645-1649",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381188"}
@article{bb387126,
AUTHOR = "Youn, J. and Jo, D.U. and Seo, S. and Kim, S. and Choi, J.W.",
TITLE = "Generating visual-adaptive audio representation for audio recognition",
JOURNAL = PRL,
VOLUME = "192",
YEAR = "2025",
PAGES = "65-71",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381189"}
@article{bb387127,
AUTHOR = "Zhao, R. and Zhang, Y.S. and Ji, J.H. and Yi, S. and Wen, W.Y. and Lan, R.",
TITLE = "AES-AUDIO: An Encryption Scheme for Audio Supporting Differentiated
Decryption",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "2268-2280",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381190"}
@article{bb387128,
AUTHOR = "Liu, Z. and Hou, Y.B. and Wang, W.W. and Michiels, S. and Hughes, D.",
TITLE = "SCAN: Selective Contrastive Learning Against Noisy Data for Acoustic
Anomaly Detection",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3355-3359",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381191"}
@article{bb387129,
AUTHOR = "Feng, M. and Zhai, G.T. and Zhang, X.P. and Hu, M.",
TITLE = "CoughSlowFast: Cough Recognition With Audio and Video Signal Fusion",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3774-3778",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381192"}
@article{bb387130,
AUTHOR = "Howard, M. and Jones, R. and Hirakawa, K.",
TITLE = "Event-Based Visual Microphone Based on Specular Reflections Off
Angularly Deformed Surfaces",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "10396-10405",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381193"}
@article{bb387131,
AUTHOR = "Ma, C.Y. and Jia, P. and Guo, H.Y. and Yang, W.M.",
TITLE = "ESTM: An Enhanced Dual-Branch Spectral-Temporal Mamba for Anomalous
Sound Detection",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3919-3923",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381194"}
@article{bb387132,
AUTHOR = "Wang, S. and Zhang, S. and Cheng, B. and Sheng, S.W.",
TITLE = "An Anomalous Sound Detection Network Based on Time-Frequency
Attention and Improved One-Class Softmax",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "4044-4048",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381195"}
@article{bb387133,
AUTHOR = "Fu, M. and Wang, X.M. and Wang, J. and Yi, Z.",
TITLE = "Synthetic Gradient Optimization-Based Implicit Amortized Bayesian
Meta-Learning for Few-Shot Pumi Spectrographic Image Recognition",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "11",
MONTH = "November",
PAGES = "10756-10771",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381196"}
@article{bb387134,
AUTHOR = "Li, S.Q. and Hu, J. and Zhao, Z. and Xu, Z.Y.",
TITLE = "Extended Node-Specific Distributed Generalized Sidelobe Canceler for
Outdoor Wireless Acoustic Sensor Networks",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "306-310",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381197"}
@article{bb387135,
AUTHOR = "Gong, Y. and Khurana, S. and Rouditchenko, A. and Glass, J.",
TITLE = "CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for
Audio Classification",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "3",
MONTH = "March",
PAGES = "3571-3585",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381198"}
@article{bb387136,
AUTHOR = "Xiong, J.Y. and Wang, J. and Wang, W. and Lyu, X. and Kwan, J.L. and Xue, J.",
TITLE = "Masked autoencoders for spatio-temporal audio representations:
heory and optimization",
JOURNAL = PR,
VOLUME = "175",
YEAR = "2026",
PAGES = "113133",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381199"}
@article{bb387137,
AUTHOR = "Hashemi, S.M.H. and Kolivand, H. and Khan, W. and Saba, T.",
TITLE = "Infant Cry Analysis: A Survey of Datasets, Features, and Machine
Learning Techniques",
JOURNAL = AffCom,
VOLUME = "17",
YEAR = "2026",
NUMBER = "1",
MONTH = "January",
PAGES = "21-40",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381200"}
@article{bb387138,
AUTHOR = "Aghazade, K. and Gholami, A.",
TITLE = "Robust Acoustic and Elastic Full Waveform Inversion by Adaptive
Tikhonov-TV Regularization",
JOURNAL = SIIMS,
VOLUME = "19",
YEAR = "2026",
NUMBER = "1",
PAGES = "480-518",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381201"}
@article{bb387139,
AUTHOR = "Desai, A. and Ma, J. and Lahivaara, T. and Monk, P.",
TITLE = "A Neural Network-Enhanced Born Approximation for Inverse Scattering",
JOURNAL = SIIMS,
VOLUME = "19",
YEAR = "2026",
NUMBER = "1",
PAGES = "302-326",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381202"}
@article{bb387140,
AUTHOR = "Liu, X.L. and Tian, J. and Zhang, B.",
TITLE = "An Inverse Obstacle Scattering Problem with Passive Data in the Time
Domain",
JOURNAL = SIIMS,
VOLUME = "19",
YEAR = "2026",
NUMBER = "1",
PAGES = "612-642",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381203"}
@article{bb387141,
AUTHOR = "Chen, C. and Zhou, J. and Chen, Y. and Li, A. and Gu, F.W. and Xi, L.",
TITLE = "Fine-tuned Whisper-based semantic-temporal aggregation networks for
sound event classification",
JOURNAL = PR,
VOLUME = "179",
YEAR = "2026",
PAGES = "113706",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381204"}
@article{bb387142,
AUTHOR = "Liang, Y.Q. and Mitchell, A. and Kang, J. and Aletta, F.",
TITLE = "A Review of Soundscape Datasets:
Challenges and Prospects for Multimodal Research",
JOURNAL = AffCom,
VOLUME = "17",
YEAR = "2026",
NUMBER = "2",
MONTH = "April",
PAGES = "1505-1520",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381205"}
@article{bb387143,
AUTHOR = "Zhuang, X. and Peeters, G. and Richard, G.",
TITLE = "AudioCAN: Enhanced Few-Shot Audio Classification via Energy-Guided
Temporal Cross Attention",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2215-2219",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381206"}
@article{bb387144,
AUTHOR = "Schmid, F. and Tang, C.I. and Parekh, S. and Ithapu, V.K. and Ortiz, J.A. and Ferroni, G. and Qian, Y.J. and Jasonas, A. and Frateanu, C. and Clark, C. and Widmer, G. and Bilen, C.",
TITLE = "Sound Event Detection With Boundary-Aware Optimization and Inference",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2340-2344",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381207"}
@article{bb387145,
AUTHOR = "Pasztor, M. and Czanik, C. and Bondar, I.",
TITLE = "A Single Array Approach for Infrasound Signal Discrimination from
Quarry Blasts via Machine Learning",
JOURNAL = RS,
VOLUME = "15",
YEAR = "2023",
NUMBER = "6",
PAGES = "1657",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381208"}
@article{bb387146,
AUTHOR = "Silber, E.A. and Bowman, D.C.",
TITLE = "Isolating the Source Region of Infrasound Travel Time Variability
Using Acoustic Sensors on High-Altitude Balloons",
JOURNAL = RS,
VOLUME = "15",
YEAR = "2023",
NUMBER = "14",
PAGES = "3661",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381209"}
@article{bb387147,
AUTHOR = "Bagad, P. and Tapaswi, M. and Snoek, C.G.M. and Zisserman, A.",
TITLE = "The Sound of Water: Inferring Physical Properties From Pouring
Liquids",
JOURNAL = PAMI,
VOLUME = "48",
YEAR = "2026",
NUMBER = "9",
MONTH = "September",
PAGES = "11111-11123",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381210"}
@article{bb387148,
AUTHOR = "Liu, Y.Y. and Karlsson, J. and Elvander, F.",
TITLE = "Sound Field Estimation Using Optimal Transport Barycenters in the
Presence of Phase Errors",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3217-3221",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381211"}
@article{bb387149,
AUTHOR = "Feng, X. and Yang, K. and Li, M.H.",
TITLE = "Data and Physics Co-Driven Prediction Method for Acoustic Field
Uncertainty",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "2939-2943",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381212"}
@article{bb387150,
AUTHOR = "Bai, J. and Rana, R. and Wu, D. and Qu, Y.Y. and Tao, X.H. and Zhang, J. and Busso, C. and Palaiahnakote, S.",
TITLE = "FedMLAC: Mutual learning driven heterogeneous federated audio
classification",
JOURNAL = PR,
VOLUME = "180",
YEAR = "2026",
PAGES = "114250",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381213"}
@article{bb387151,
AUTHOR = "Yin, H. and Guo, S. and Jia, X. and Xu, X. and Zhang, L. and Liu, S. and Wang, D. and Lu, H.C. and Xue, T.F.",
TITLE = "EvMic: Event-Based Non-Contact Sound Recovery From Effective
Spatial-Temporal Modeling",
JOURNAL = IP,
VOLUME = "35",
YEAR = "2026",
PAGES = "9923-9934",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381214"}
@article{bb387152,
AUTHOR = "Jung, J. and Kim, J.H. and Shin, I. and Chung, J.S.",
TITLE = "SCORE: Scaling Audio Generation Using Standardized COmposite REwards",
JOURNAL = SPLetters,
VOLUME = "33",
YEAR = "2026",
PAGES = "3391-3395",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381215"}
@article{bb387153,
AUTHOR = "Zhao, L. and Chen, S. and Feng, L.F. and Zhang, J.C. and Zhang, X.L. and Zhang, C. and Li, X.L.",
TITLE = "DualSpec: Text-to-Spatial-Audio Generation via Dual-Spectrogram
Guided Diffusion Model",
JOURNAL = MultMed,
VOLUME = "28",
YEAR = "2026",
PAGES = "7112-7123",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381216"}
@inproceedings{bb387154,
AUTHOR = "Gao, H.Y. and Ma, J.H. and Ahmedt Aristizabal, D. and Nguyen, C. and Liu, M.M.",
TITLE = "SOAF: Scene Occlusion-aware Neural Acoustic Field",
BOOKTITLE = WACV26,
YEAR = "2026",
PAGES = "4097-4107",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381217"}
@inproceedings{bb387155,
AUTHOR = "Kratky, A. and Hwang, J.",
TITLE = "Inner Voices: Reflexive Augmented Listening",
BOOKTITLE = VAMR23,
YEAR = "2023",
PAGES = "233-252",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381218"}
@inproceedings{bb387156,
AUTHOR = "Chen, M.F. and Gebru, I.D. and Ananthabhotla, I. and Richardt, C. and Markovic, D. and Sandakly, J. and Krenn, S. and Keebler, T. and Shlizerman, E. and Richard, A.",
TITLE = "SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic
Binding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8331-8341",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381219"}
@inproceedings{bb387157,
AUTHOR = "Chen, Z.Y. and Seetharaman, P. and Russell, B. and Nieto, O. and Bourgin, D. and Owens, A. and Salamon, J.",
TITLE = "Video-Guided Foley Sound Generation with Multimodal Controls",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18770-18781",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381220"}
@inproceedings{bb387158,
AUTHOR = "Qi, F. and Ma, K. and Xu, C.S.",
TITLE = "Customized Condition Controllable Generation for Video Soundtrack",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23914-23924",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381221"}
@inproceedings{bb387159,
AUTHOR = "Huang, C. and Gao, R.H. and Tsang, J.M.F. and Kurcius, J. and Bilen, C. and Xu, C.L. and Kumar, A. and Parekh, S.",
TITLE = "Learning to Highlight Audio by Watching Movies",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23925-23935",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381222"}
@inproceedings{bb387160,
AUTHOR = "Fang, B. and Wu, W.H. and Wu, Q.Q. and Song, Y.X. and Chan, A.B.",
TITLE = "DistinctAD: Distinctive Audio Description Generation in Contexts",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13571-13581",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381223"}
@inproceedings{bb387161,
AUTHOR = "Wang, Z.Y. and Xu, X.W. and Wang, X.D. and Zhou, H.S.",
TITLE = "GWO-GEA: A Black-box Method for Generating Audio Adversarial Examples",
BOOKTITLE = ICIVC24,
YEAR = "2024",
PAGES = "439-444",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381224"}
@inproceedings{bb387162,
AUTHOR = "Huang, C. and Markovic, D. and Xu, C.L. and Richard, A.",
TITLE = "Modeling and Driving Human Body Soundfields Through Acoustic Primitives",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "X: 1-17",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381225"}
@inproceedings{bb387163,
AUTHOR = "Ma, J. and Wang, W.G. and Yang, Y. and Zheng, F.",
TITLE = "Mutual Learning for Acoustic Matching and Dereverberation via Visual
Scene-driven Diffusion",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVIII: 331-349",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381226"}
@inproceedings{bb387164,
AUTHOR = "Li, T. and Wang, R. and Huang, P.Y. and Owens, A. and Anumanchipalli, G.",
TITLE = "Self-supervised Audio-visual Soundscape Stylization",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXX: 20-40",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381227"}
@inproceedings{bb387165,
AUTHOR = "Xie, J.Y. and Han, T.D. and Bain, M. and Nagrani, A. and Varol, G. and Xie, W. and Zisserman, A.",
TITLE = "Autoad-zero: A Training-free Framework for Zero-shot Audio Description",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 81-97",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381228"}
@inproceedings{bb387166,
AUTHOR = "Xie, Z.F. and Yu, S.Y. and He, Q. and Li, M.T.",
TITLE = "Sonic VisionLM: Playing Sound with Vision Language Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26856-26865",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381229"}
@inproceedings{bb387167,
AUTHOR = "Ratnarajah, A. and Ghosh, S. and Kumar, S. and Chiniya, P. and Manocha, D.",
TITLE = "AV-RIR: Audio-Visual Room Impulse Response Estimation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "27154-27165",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381230"}
@inproceedings{bb387168,
AUTHOR = "Chen, Z.Y. and Gebru, I.D. and Richardt, C. and Kumar, A. and Laney, W. and Owens, A. and Richard, A.",
TITLE = "Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and
Benchmark",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "21886-21896",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381231"}
@inproceedings{bb387169,
AUTHOR = "Wang, M.L. and Sawata, R. and Clarke, S. and Gao, R.H. and Wu, S.Z. and Wu, J.J.",
TITLE = "Hearing Anything Anywhere",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "11790-11799",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381232"}
@inproceedings{bb387170,
AUTHOR = "Chowdhury, S. and Ghosh, S. and Dasgupta, S. and Ratnarajah, A. and Tyagi, U. and Manocha, D.",
TITLE = "AdVerb: Visually Guided Audio Dereverberation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7850-7862",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381233"}
@inproceedings{bb387171,
AUTHOR = "Rios, B. and Martinez, E. and Silvera, D. and Cancela, P. and Capdehourat, G.",
TITLE = "Teaching Practices Analysis Through Audio Signal Processing",
BOOKTITLE = CIARP23,
YEAR = "2023",
PAGES = "I:133-147",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381234"}
@inproceedings{bb387172,
AUTHOR = "Chen, C. and Richard, A. and Shapovalov, R. and Ithapu, V.K. and Neverova, N. and Grauman, K. and Vedaldi, A.",
TITLE = "Novel-View Acoustic Synthesis",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6409-6419",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381235"}
@inproceedings{bb387173,
AUTHOR = "Du, Y.X. and Chen, Z.Y. and Salamon, J. and Russell, B. and Owens, A.",
TITLE = "Conditional Generation of Audio from Video via Foley Analogies",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "2426-2436",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381236"}
@inproceedings{bb387174,
AUTHOR = "Clarke, S. and Gao, R.H. and Wang, M. and Rau, M. and Xu, J. and Wang, J.H. and James, D.L. and Wu, J.J.",
TITLE = "REALIMPACT: A Dataset of Impact Sound Fields for Real Objects",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1516-1525",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381237"}
@inproceedings{bb387175,
AUTHOR = "Su, K. and Qian, K. and Shlizerman, E. and Torralba, A. and Gan, C.",
TITLE = "Physics-Driven Diffusion Models for Impact Sound Synthesis from
Videos",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "9749-9759",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381238"}
@inproceedings{bb387176,
AUTHOR = "Martinez Canete, Y. and Sahli, H. and Berenguer, A.D.",
TITLE = "Multi-view Infant Cry Classification",
BOOKTITLE = IbPRIA23,
YEAR = "2023",
PAGES = "639-653",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381239"}
@inproceedings{bb387177,
AUTHOR = "Zhang, Q. and Yang, J.B. and Zhang, X.W. and Cao, T.Y.",
TITLE = "Generating Adversarial Examples in Audio Classification with
Generative Adversarial Network",
BOOKTITLE = ICIVC22,
YEAR = "2022",
PAGES = "848-853",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381240"}
@inproceedings{bb387178,
AUTHOR = "Yu, B.C. and Liao, C. and Xu, W.X. and Wei, M. and Lv, C. and Li, J.X.",
TITLE = "Environmental Sound Detection based on Acoustic Multidimensional
Synergistic Features and MobileNet-EAL",
BOOKTITLE = ICRVC22,
YEAR = "2022",
PAGES = "234-238",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381241"}
@inproceedings{bb387179,
AUTHOR = "Chen, B.Q. and Bondi, L. and Das, S.",
TITLE = "Learning to Adapt to Domain Shifts with Few-shot Samples in Anomalous
Sound Detection",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "133-139",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381242"}
@inproceedings{bb387180,
AUTHOR = "Singh, N. and Mentch, J. and Ng, J. and Beveridge, M. and Drori, I.",
TITLE = "Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis",
BOOKTITLE = ICCV21,
YEAR = "2021",
PAGES = "286-295",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381243"}
@inproceedings{bb387181,
AUTHOR = "Higham, D. and Bagla, A. and Haralampieva, V.",
TITLE = "A No-Reference model for Detecting Audio Artifacts using Pretrained
Audio Neural Networks",
BOOKTITLE = VAQuality22,
YEAR = "2022",
PAGES = "9-13",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381244"}
@inproceedings{bb387182,
AUTHOR = "Ludovico, L.A. and Ntalampiras, S. and Presti, G. and Cannas, S. and Battini, M. and Mattiello, S.",
TITLE = "Catmeows: A Publicly-available Dataset of Cat Vocalizations",
BOOKTITLE = MMMod21,
YEAR = "2021",
PAGES = "II:230-243",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381245"}
@inproceedings{bb387183,
AUTHOR = "Duan, B. and Wang, W. and Tang, H. and Latapie, H. and Yan, Y.",
TITLE = "Cascade Attention Guided Residue Learning GAN for Cross-Modal
Translation",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "1336-1343",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381246"}
@inproceedings{bb387184,
AUTHOR = "Guzhov, A. and Raue, F. and Hees, J. and Dengel, A.",
TITLE = "ESResNet: Environmental Sound Classification Based on Visual Domain
Models",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "4933-4940",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381247"}
@inproceedings{bb387185,
AUTHOR = "Rocha, B.M. and Pessoa, D. and Marques, A. and Carvalho, P. and Paiva, R.P.",
TITLE = "Influence of Event Duration on Automatic Wheeze Classification",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "7462-7469",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381248"}
@inproceedings{bb387186,
AUTHOR = "Greco, A. and Roberto, A. and Saggese, A. and Vento, M.",
TITLE = "Which are the factors affecting the performance of audio surveillance
systems?",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "7876-7883",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381249"}
@inproceedings{bb387187,
AUTHOR = "Sallo, R.A. and Esmaeilpour, M. and Cardinal, P.",
TITLE = "Adversarially Training for Audio Classifiers",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "9569-9576",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381250"}
@inproceedings{bb387188,
AUTHOR = "Giacalone, G. and Lo Bosco, G. and Barra, M. and Bonanno, A. and Buscaino, G. and Noormets, R. and Nuth, C. and Calabro, M. and Basilone, G. and Genovese, S. and Fontana, I. and Mazzola, S. and Rizzo, R. and Aronica, S.",
TITLE = "Pattern Classification from Multi-beam Acoustic Data Acquired in
Kongsfjorden",
BOOKTITLE = MAES20,
YEAR = "2020",
PAGES = "55-64",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381251"}
@inproceedings{bb387189,
AUTHOR = "Papapanagiotou, V. and Diou, C. and van den Boer, J. and Mars, M. and Delopoulos, A.",
TITLE = "Recognition of Food-texture Attributes Using an In-ear Microphone",
BOOKTITLE = MADiMa20,
YEAR = "2020",
PAGES = "558-570",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381252"}
@inproceedings{bb387190,
AUTHOR = "Dubey, R. and Bharadwaj, S. and Zafar, M.I. and Sharma, V.B. and Biswas, S.",
TITLE = "Collaborative Noise Mapping Using Smartphone",
BOOKTITLE = ISPRS20,
YEAR = "2020",
PAGES = "B4:253-260",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381253"}
@inproceedings{bb387191,
AUTHOR = "Sanguineti, V. and Morerio, P. and Pozzetti, N. and Greco, D. and Cristani, M. and Murino, V.",
TITLE = "Leveraging Acoustic Images for Effective Self-supervised Audio
Representation Learning",
BOOKTITLE = ECCV20,
YEAR = "2020",
PAGES = "XXII:119-135",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381254"}
@inproceedings{bb387192,
AUTHOR = "Kadmiri, I.E. and Elamri, F.Z. and Ben Ali, Y. and Khaled, A. and Miad, A.K.E. and Bria, D.",
TITLE = "Induced guided acoustic waves by the presence of a defective guide in
one dimensional asymmetric loop phononic crystal",
BOOKTITLE = ISCV20,
YEAR = "2020",
PAGES = "1-8",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381255"}
@inproceedings{bb387193,
AUTHOR = "Ramaswamy, J. and Das, S.",
TITLE = "See the Sound, Hear the Pixels",
BOOKTITLE = WACV20,
YEAR = "2020",
PAGES = "2959-2968",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381256"}
@inproceedings{bb387194,
AUTHOR = "Zhao, H. and Gan, C. and Ma, W. and Torralba, A.B.",
TITLE = "The Sound of Motions",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "1735-1744",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381257"}
@inproceedings{bb387195,
AUTHOR = "Hu, D. and Nie, F.P. and Li, X.L.",
TITLE = "Deep Multimodal Clustering for Unsupervised Audiovisual Learning",
BOOKTITLE = CVPR19,
YEAR = "2019",
PAGES = "9240-9249",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381258"}
@inproceedings{bb387196,
AUTHOR = "Foggia, P. and Saggese, A. and Strisciuglio, N. and Vento, M. and Vigilante, V.",
TITLE = "Detecting Sounds of Interest in Roads with Deep Networks",
BOOKTITLE = CIAP19,
YEAR = "2019",
PAGES = "II:583-592",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381259"}
@inproceedings{bb387197,
AUTHOR = "Liu, X.H. and Delany, S.J. and McKeever, S.",
TITLE = "Sound Transformation: Applying Image Neural Style Transfer Networks to
Audio Spectograms",
BOOKTITLE = CAIP19,
YEAR = "2019",
PAGES = "II:330-341",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381260"}
@inproceedings{bb387198,
AUTHOR = "Giannakopoulos, T. and Orfanidi, M. and Perantonis, S.",
TITLE = "Athens Urban Soundscape (ATHUS):
A Dataset for Urban Soundscape Quality Recognition",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "I:338-348",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381261"}
@inproceedings{bb387199,
AUTHOR = "Jiang, Y. and Leung, F.H.F.",
TITLE = "Discriminative Collaborative Representation and Its Application to
Audio Signal Classification",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "31-36",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT381262"}
Last update:Sep 30, 2026 at 11:45:00