@article{bb383600,
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#TT377681"}
@article{bb383601,
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#TT377682"}
@article{bb383602,
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#TT377683"}
@article{bb383603,
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#TT377684"}
@article{bb383604,
AUTHOR = "Kuzmanovic, Z. and Cubrilovic, S. and Punt, M. and Vucic, D. and Kovacevic, B.",
TITLE = "Characterization of OFDM-Based Secure Data Transmission Over Voice
Channels",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "3230-3234",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377685"}
@article{bb383605,
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#TT377686"}
@article{bb383606,
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#TT377687"}
@article{bb383607,
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#TT377688"}
@article{bb383608,
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#TT377689"}
@article{bb383609,
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#TT377690"}
@article{bb383610,
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#TT377691"}
@article{bb383611,
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#TT377692"}
@article{bb383612,
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#TT377693"}
@article{bb383613,
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#TT377694"}
@article{bb383614,
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#TT377695"}
@article{bb383615,
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#TT377696"}
@article{bb383616,
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#TT377697"}
@article{bb383617,
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#TT377698"}
@article{bb383618,
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#TT377699"}
@article{bb383619,
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#TT377700"}
@article{bb383620,
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#TT377701"}
@article{bb383621,
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#TT377702"}
@article{bb383622,
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#TT377703"}
@article{bb383623,
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#TT377704"}
@article{bb383624,
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#TT377705"}
@article{bb383625,
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#TT377706"}
@article{bb383626,
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#TT377707"}
@article{bb383627,
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#TT377708"}
@inproceedings{bb383628,
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#TT377709"}
@inproceedings{bb383629,
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#TT377710"}
@inproceedings{bb383630,
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#TT377711"}
@inproceedings{bb383631,
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#TT377712"}
@inproceedings{bb383632,
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#TT377713"}
@inproceedings{bb383633,
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#TT377714"}
@inproceedings{bb383634,
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#TT377715"}
@inproceedings{bb383635,
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#TT377716"}
@inproceedings{bb383636,
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#TT377717"}
@inproceedings{bb383637,
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#TT377718"}
@inproceedings{bb383638,
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#TT377719"}
@inproceedings{bb383639,
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#TT377720"}
@inproceedings{bb383640,
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#TT377721"}
@inproceedings{bb383641,
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#TT377722"}
@inproceedings{bb383642,
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#TT377723"}
@inproceedings{bb383643,
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#TT377724"}
@inproceedings{bb383644,
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#TT377725"}
@inproceedings{bb383645,
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#TT377726"}
@inproceedings{bb383646,
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#TT377727"}
@inproceedings{bb383647,
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#TT377728"}
@inproceedings{bb383648,
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#TT377729"}
@inproceedings{bb383649,
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#TT377730"}
@inproceedings{bb383650,
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#TT377731"}
@inproceedings{bb383651,
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#TT377732"}
@inproceedings{bb383652,
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#TT377733"}
@inproceedings{bb383653,
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#TT377734"}
@inproceedings{bb383654,
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#TT377735"}
@inproceedings{bb383655,
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#TT377736"}
@inproceedings{bb383656,
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#TT377737"}
@inproceedings{bb383657,
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#TT377738"}
@inproceedings{bb383658,
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#TT377739"}
@inproceedings{bb383659,
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#TT377740"}
@inproceedings{bb383660,
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#TT377741"}
@inproceedings{bb383661,
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#TT377742"}
@inproceedings{bb383662,
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#TT377743"}
@inproceedings{bb383663,
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#TT377744"}
@inproceedings{bb383664,
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#TT377745"}
@inproceedings{bb383665,
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#TT377746"}
@inproceedings{bb383666,
AUTHOR = "San Juan, E. and Firoozabadi, A.D. and Soto, I. and Adasme, P. and Canete, L.",
TITLE = "Proposed Integration Algorithm to Optimize the Separation of Audio
Signals Using the Ica and Wavelet Transform",
BOOKTITLE = ICISP20,
YEAR = "2020",
PAGES = "367-376",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377747"}
@inproceedings{bb383667,
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#TT377748"}
@inproceedings{bb383668,
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#TT377749"}
@inproceedings{bb383669,
AUTHOR = "Gao, R. and Grauman, K.",
TITLE = "Co-Separating Sounds of Visual Objects",
BOOKTITLE = ICCV19,
YEAR = "2019",
PAGES = "3878-3887",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377750"}
@inproceedings{bb383670,
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#TT377751"}
@inproceedings{bb383671,
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#TT377752"}
@inproceedings{bb383672,
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#TT377753"}
@inproceedings{bb383673,
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#TT377754"}
@inproceedings{bb383674,
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#TT377755"}
@inproceedings{bb383675,
AUTHOR = "Chong, D. and Zou, Y.X. and Wang, W.W.",
TITLE = "Multi-channel Convolutional Neural Networks with Multi-level Feature
Fusion for Environmental Sound Classification",
BOOKTITLE = "MMMod19",
YEAR = "2019",
PAGES = "II:157-168",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377756"}
@inproceedings{bb383676,
AUTHOR = "Zhang, X. and Zou, Y. and Wang, W.",
TITLE = "LD-CNN: A Lightweight Dilated Convolutional Neural Network for
Environmental Sound Classification",
BOOKTITLE = ICPR18,
YEAR = "2018",
PAGES = "373-378",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377757"}
@inproceedings{bb383677,
AUTHOR = "Sterling, A. and Wilson, J. and Lowe, S. and Lin, M.C.",
TITLE = "ISNN: Impact Sound Neural Network for Audio-Visual Object
Classification",
BOOKTITLE = ECCV18,
YEAR = "2018",
PAGES = "XV: 578-595",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377758"}
@inproceedings{bb383678,
AUTHOR = "Tak, R.N. and Agrawal, D.M. and Patil, H.A.",
TITLE = "Novel Phase Encoded Mel Filterbank Energies for Environmental Sound
Classification",
BOOKTITLE = PReMI17,
YEAR = "2017",
PAGES = "317-325",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377759"}
@inproceedings{bb383679,
AUTHOR = "Zhu, M. and Shahnawaz, M. and Tubaro, S. and Sarti, A.",
TITLE = "HRTF personalization based on weighted sparse representation of
anthropometric features",
BOOKTITLE = IC3D17,
YEAR = "2017",
PAGES = "1-7",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377760"}
@inproceedings{bb383680,
AUTHOR = "Joshi, G. and Dandvate, C. and Tiwari, H. and Mundhare, A.",
TITLE = "Prediction of Probability of Crying of a Child and System Formation
for Cry Detection and Financial Viability of the System",
BOOKTITLE = ICVISP17,
YEAR = "2017",
PAGES = "134-141",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377761"}
@inproceedings{bb383681,
AUTHOR = "Dentamaro, G. and Cardellicchio, A. and Guaragnella, C.",
TITLE = "Real time Artificial Auditory Systems for cluttered environments",
BOOKTITLE = ICPR16,
YEAR = "2016",
PAGES = "2234-2239",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377762"}
@inproceedings{bb383682,
AUTHOR = "Fraj, O. and Ghozi, R. and Jaidane Saidane, M.",
TITLE = "Texturedness decision time for audio texturedness indicator",
BOOKTITLE = ISIVC16,
YEAR = "2016",
PAGES = "174-179",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377763"}
@inproceedings{bb383683,
AUTHOR = "Rashid, H. and Ahmed, I.U. and Reza, S.M.T. and Islam, M.A.",
TITLE = "Solar powered smart ultrasonic insects repellent with DTMF and manual
control for agriculture",
BOOKTITLE = IVPR17,
YEAR = "2017",
PAGES = "1-5",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377764"}
@inproceedings{bb383684,
AUTHOR = "Song, Y.C. and Wang, X.C. and Yang, C. and Gao, G. and Chen, W. and Tu, W.P.",
TITLE = "Frame-Independent and Parallel Method for 3D Audio Real-Time Rendering
on Mobile Devices",
BOOKTITLE = MMMod17,
YEAR = "2017",
PAGES = "II: 221-232",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377765"}
@inproceedings{bb383685,
AUTHOR = "Li, G. and Wang, X.C. and Gao, L. and Hu, R.M. and Li, D.S.",
TITLE = "The Perceptual Lossless Quantization of Spatial Parameter for 3D Audio
Signals",
BOOKTITLE = MMMod17,
YEAR = "2017",
PAGES = "II: 381-392",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377766"}
@inproceedings{bb383686,
AUTHOR = "Wang, S. and Hu, R.M. and Chen, S.H. and Wang, X.C. and Yang, Y.H. and Tu, W.P. and Peng, B.",
TITLE = "3D Sound Field Reproduction at Non Central Point for NHK 22.2 System",
BOOKTITLE = MMMod17,
YEAR = "2017",
PAGES = "I: 3-14",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377767"}
@inproceedings{bb383687,
AUTHOR = "Owens, A. and Isola, P. and McDermott, J. and Torralba, A.B. and Adelson, E.H. and Freeman, W.T.",
TITLE = "Visually Indicated Sounds",
BOOKTITLE = CVPR16,
YEAR = "2016",
PAGES = "2405-2413",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377768"}
@inproceedings{bb383688,
AUTHOR = "Wang, L. and Cavallaro, A.",
TITLE = "Ear in the sky:
Ego-noise reduction for auditory micro aerial vehicles",
BOOKTITLE = AVSS16,
YEAR = "2016",
PAGES = "152-158",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377769"}
@inproceedings{bb383689,
AUTHOR = "Xie, J. and Towsey, M. and Zhang, L. and Zhang, J.L. and Roe, P.",
TITLE = "Feature Extraction Based on Bandpass Filtering for Frog Call
Classification",
BOOKTITLE = ICISP16,
YEAR = "2016",
PAGES = "231-239",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377770"}
@inproceedings{bb383690,
AUTHOR = "Wassi, G. and Iloga, S. and Romain, O. and Granado, B.",
TITLE = "FPGA-based real-time MFCC extraction for automatic audio indexing on
FM broadcast data",
BOOKTITLE = DASIP15,
YEAR = "2015",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377771"}
@inproceedings{bb383691,
AUTHOR = "Wu, T.Z. and Hu, R.M. and Gao, L. and Wang, X.C. and Ke, S.F.",
TITLE = "Analysis and Comparison of Inter-Channel Level Difference and
Interaural Level Difference",
BOOKTITLE = MMMod16,
YEAR = "2016",
PAGES = "I: 586-595",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377772"}
@inproceedings{bb383692,
AUTHOR = "Shen, J. and Nie, L.Q. and Chua, T.S.",
TITLE = "Smart Ambient Sound Analysis via Structured Statistical Modeling",
BOOKTITLE = MMMod16,
YEAR = "2016",
PAGES = "II: 231-243",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377773"}
@inproceedings{bb383693,
AUTHOR = "Zhang, L.K. and Hu, R.M. and Li, D.S. and Wang, X.C. and Tu, W.P.",
TITLE = "Adaptive Multichannel Reduction Using Convex Polyhedral Loudspeaker
Array",
BOOKTITLE = MMMod16,
YEAR = "2016",
PAGES = "I: 421-431",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377774"}
@inproceedings{bb383694,
AUTHOR = "Kular, D. and Hollowood, K. and Ommojaro, O. and Smart, K. and Bush, M. and Ribeiro, E.",
TITLE = "Classifying Frog Calls Using Gaussian Mixture Models",
BOOKTITLE = ISVC15,
YEAR = "2015",
PAGES = "II: 347-354",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377775"}
@inproceedings{bb383695,
AUTHOR = "Xie, J. and Towsey, M. and Zhang, J.L. and Dong, X. and Roe, P.",
TITLE = "Application of image processing techniques for frog call
classification",
BOOKTITLE = ICIP15,
YEAR = "2015",
PAGES = "4190-4194",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377776"}
@inproceedings{bb383696,
AUTHOR = "Papapanagiotou, V. and Diou, C. and Zhou, L.C. and van den Boer, J. and Mars, M. and Delopoulos, A.",
TITLE = "Fractal Nature of Chewing Sounds",
BOOKTITLE = MADiMa15,
YEAR = "2015",
PAGES = "401-408",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377777"}
@inproceedings{bb383697,
AUTHOR = "Lamkadam, A. and Karim, M.",
TITLE = "Comparative study and improvement of acoustic vectors extractors:
Multiple streams applied to the recognition of Arabic numerals",
BOOKTITLE = ISCV15,
YEAR = "2015",
PAGES = "1-9",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377778"}
@inproceedings{bb383698,
AUTHOR = "Lindeberg, T. and Friberg, A.",
TITLE = "Scale-Space Theory for Auditory Signals",
BOOKTITLE = SSVM15,
YEAR = "2015",
PAGES = "3-15",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377779"}
@inproceedings{bb383699,
AUTHOR = "Unaffiliated, E.M.S.",
TITLE = "Representing pictures with sound",
BOOKTITLE = AIPR14,
YEAR = "2014",
PAGES = "1-2",
BIBSOURCE = "http://www.visionbib.com/bibliography/other1022.html#TT377780"}
Last update:Aug 19, 2026 at 13:26:35