Visually Indicated Sounds. Owens, A., Isola, P., McDermott, J. H., Torralba, A., Adelson, E. H., & Freeman, W. T. Cvpr, 2016. arXiv: 1512.08512 ISBN: 9781467388511
Paper doi abstract bibtex Materials make distinctive sounds when they are hit or scratched – dirt makes a thud; ceramic makes a clink. These sounds reveal aspects of an object's material properties, as well as the force and motion of the physical interaction. In this paper, we introduce an algorithm that learns to synthesize sound from videos of people hitting objects with a drumstick. The algorithm uses a recurrent neural network to predict sound features from videos and then produces a waveform from these features with an example-based synthesis procedure. We demonstrate that the sounds generated by our model are realistic enough to fool participants in a "real or fake" psychophysical experiment, and that they convey significant information about the material properties in a scene.
@article{owens_visually_2016,
title = {Visually {Indicated} {Sounds}},
issn = {10636919},
url = {http://arxiv.org/abs/1512.08512},
doi = {10.1109/CVPR.2016.264},
abstract = {Materials make distinctive sounds when they are hit or scratched -- dirt makes a thud; ceramic makes a clink. These sounds reveal aspects of an object's material properties, as well as the force and motion of the physical interaction. In this paper, we introduce an algorithm that learns to synthesize sound from videos of people hitting objects with a drumstick. The algorithm uses a recurrent neural network to predict sound features from videos and then produces a waveform from these features with an example-based synthesis procedure. We demonstrate that the sounds generated by our model are realistic enough to fool participants in a "real or fake" psychophysical experiment, and that they convey significant information about the material properties in a scene.},
journal = {Cvpr},
author = {Owens, Andrew and Isola, Phillip and McDermott, Josh H. and Torralba, Antonio and Adelson, Edward H. and Freeman, William T.},
year = {2016},
note = {arXiv: 1512.08512
ISBN: 9781467388511},
}
Downloads: 0
{"_id":"TkfojLpfW9kkqb8h2","bibbaseid":"owens-isola-mcdermott-torralba-adelson-freeman-visuallyindicatedsounds-2016","author_short":["Owens, A.","Isola, P.","McDermott, J. H.","Torralba, A.","Adelson, E. H.","Freeman, W. T."],"bibdata":{"bibtype":"article","type":"article","title":"Visually Indicated Sounds","issn":"10636919","url":"http://arxiv.org/abs/1512.08512","doi":"10.1109/CVPR.2016.264","abstract":"Materials make distinctive sounds when they are hit or scratched – dirt makes a thud; ceramic makes a clink. These sounds reveal aspects of an object's material properties, as well as the force and motion of the physical interaction. In this paper, we introduce an algorithm that learns to synthesize sound from videos of people hitting objects with a drumstick. The algorithm uses a recurrent neural network to predict sound features from videos and then produces a waveform from these features with an example-based synthesis procedure. We demonstrate that the sounds generated by our model are realistic enough to fool participants in a \"real or fake\" psychophysical experiment, and that they convey significant information about the material properties in a scene.","journal":"Cvpr","author":[{"propositions":[],"lastnames":["Owens"],"firstnames":["Andrew"],"suffixes":[]},{"propositions":[],"lastnames":["Isola"],"firstnames":["Phillip"],"suffixes":[]},{"propositions":[],"lastnames":["McDermott"],"firstnames":["Josh","H."],"suffixes":[]},{"propositions":[],"lastnames":["Torralba"],"firstnames":["Antonio"],"suffixes":[]},{"propositions":[],"lastnames":["Adelson"],"firstnames":["Edward","H."],"suffixes":[]},{"propositions":[],"lastnames":["Freeman"],"firstnames":["William","T."],"suffixes":[]}],"year":"2016","note":"arXiv: 1512.08512 ISBN: 9781467388511","bibtex":"@article{owens_visually_2016,\n\ttitle = {Visually {Indicated} {Sounds}},\n\tissn = {10636919},\n\turl = {http://arxiv.org/abs/1512.08512},\n\tdoi = {10.1109/CVPR.2016.264},\n\tabstract = {Materials make distinctive sounds when they are hit or scratched -- dirt makes a thud; ceramic makes a clink. These sounds reveal aspects of an object's material properties, as well as the force and motion of the physical interaction. In this paper, we introduce an algorithm that learns to synthesize sound from videos of people hitting objects with a drumstick. The algorithm uses a recurrent neural network to predict sound features from videos and then produces a waveform from these features with an example-based synthesis procedure. We demonstrate that the sounds generated by our model are realistic enough to fool participants in a \"real or fake\" psychophysical experiment, and that they convey significant information about the material properties in a scene.},\n\tjournal = {Cvpr},\n\tauthor = {Owens, Andrew and Isola, Phillip and McDermott, Josh H. and Torralba, Antonio and Adelson, Edward H. and Freeman, William T.},\n\tyear = {2016},\n\tnote = {arXiv: 1512.08512\nISBN: 9781467388511},\n}\n\n\n\n","author_short":["Owens, A.","Isola, P.","McDermott, J. H.","Torralba, A.","Adelson, E. H.","Freeman, W. T."],"key":"owens_visually_2016","id":"owens_visually_2016","bibbaseid":"owens-isola-mcdermott-torralba-adelson-freeman-visuallyindicatedsounds-2016","role":"author","urls":{"Paper":"http://arxiv.org/abs/1512.08512"},"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/peerherholz","dataSources":["JWysPm6bugYqREXu5"],"keywords":[],"search_terms":["visually","indicated","sounds","owens","isola","mcdermott","torralba","adelson","freeman"],"title":"Visually Indicated Sounds","year":2016}