Unsupervised feature learning for audio classification using convolutional deep belief networks. Lee, H., Pham, P., Largman, Y, & Ng, A. In Advances in neural information processing systems, pages 1–9, 2009. arXiv: 1301.3605v3 ISSN: 02643294doi abstract bibtex In recent years, deep learning approaches have gained significant interest as a way of building hierarchical representations from unlabeled data. However, to our knowledge, these deep learning approaches have not been extensively studied for auditory data. In this paper, we apply convolutional deep belief networks to audio data and empirically evaluate them on various audio classification tasks. In the case of speech data, we show that the learned features correspond to phones/phonemes. In addition, our feature representations learned from unlabeled audio data show very good performance for multiple audio classification tasks. We hope that this paper will inspire more research on deep learning approaches applied to a wide range of audio recognition tasks.
@inproceedings{Lee2009a,
title = {Unsupervised feature learning for audio classification using convolutional deep belief networks},
isbn = {978-1-60558-516-1},
doi = {10.1145/1553374.1553453},
abstract = {In recent years, deep learning approaches have gained significant interest as a way of building hierarchical representations from unlabeled data. However, to our knowledge, these deep learning approaches have not been extensively studied for auditory data. In this paper, we apply convolutional deep belief networks to audio data and empirically evaluate them on various audio classification tasks. In the case of speech data, we show that the learned features correspond to phones/phonemes. In addition, our feature representations learned from unlabeled audio data show very good performance for multiple audio classification tasks. We hope that this paper will inspire more research on deep learning approaches applied to a wide range of audio recognition tasks.},
booktitle = {Advances in neural information processing systems},
author = {Lee, Honglak and Pham, Pt and Largman, Y and Ng, Ay},
year = {2009},
pmid = {20957573},
note = {arXiv: 1301.3605v3
ISSN: 02643294},
pages = {1--9},
}
Downloads: 0
{"_id":"jz3meuGvXR32dY9Ys","bibbaseid":"lee-pham-largman-ng-unsupervisedfeaturelearningforaudioclassificationusingconvolutionaldeepbeliefnetworks-2009","downloads":0,"creationDate":"2018-10-05T11:34:48.282Z","title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author_short":["Lee, H.","Pham, P.","Largman, Y","Ng, A."],"year":2009,"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/girdhar","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","isbn":"978-1-60558-516-1","doi":"10.1145/1553374.1553453","abstract":"In recent years, deep learning approaches have gained significant interest as a way of building hierarchical representations from unlabeled data. However, to our knowledge, these deep learning approaches have not been extensively studied for auditory data. In this paper, we apply convolutional deep belief networks to audio data and empirically evaluate them on various audio classification tasks. In the case of speech data, we show that the learned features correspond to phones/phonemes. In addition, our feature representations learned from unlabeled audio data show very good performance for multiple audio classification tasks. We hope that this paper will inspire more research on deep learning approaches applied to a wide range of audio recognition tasks.","booktitle":"Advances in neural information processing systems","author":[{"propositions":[],"lastnames":["Lee"],"firstnames":["Honglak"],"suffixes":[]},{"propositions":[],"lastnames":["Pham"],"firstnames":["Pt"],"suffixes":[]},{"propositions":[],"lastnames":["Largman"],"firstnames":["Y"],"suffixes":[]},{"propositions":[],"lastnames":["Ng"],"firstnames":["Ay"],"suffixes":[]}],"year":"2009","pmid":"20957573","note":"arXiv: 1301.3605v3 ISSN: 02643294","pages":"1–9","bibtex":"@inproceedings{Lee2009a,\n\ttitle = {Unsupervised feature learning for audio classification using convolutional deep belief networks},\n\tisbn = {978-1-60558-516-1},\n\tdoi = {10.1145/1553374.1553453},\n\tabstract = {In recent years, deep learning approaches have gained significant interest as a way of building hierarchical representations from unlabeled data. However, to our knowledge, these deep learning approaches have not been extensively studied for auditory data. In this paper, we apply convolutional deep belief networks to audio data and empirically evaluate them on various audio classification tasks. In the case of speech data, we show that the learned features correspond to phones/phonemes. In addition, our feature representations learned from unlabeled audio data show very good performance for multiple audio classification tasks. We hope that this paper will inspire more research on deep learning approaches applied to a wide range of audio recognition tasks.},\n\tbooktitle = {Advances in neural information processing systems},\n\tauthor = {Lee, Honglak and Pham, Pt and Largman, Y and Ng, Ay},\n\tyear = {2009},\n\tpmid = {20957573},\n\tnote = {arXiv: 1301.3605v3\nISSN: 02643294},\n\tpages = {1--9},\n}\n\n","author_short":["Lee, H.","Pham, P.","Largman, Y","Ng, A."],"key":"Lee2009a","id":"Lee2009a","bibbaseid":"lee-pham-largman-ng-unsupervisedfeaturelearningforaudioclassificationusingconvolutionaldeepbeliefnetworks-2009","role":"author","urls":{},"metadata":{"authorlinks":{}},"html":""},"search_terms":["unsupervised","feature","learning","audio","classification","using","convolutional","deep","belief","networks","lee","pham","largman","ng"],"keywords":[],"authorIDs":[],"dataSources":["EmYaiv9TCHbg7caTW","XFrKPG99s5t3W7xuW"]}