A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging. Choi, K., Fazekas, G., Sandler, M., & Cho, K. In 2018 26th European Signal Processing Conference (EUSIPCO), pages 1870-1874, Sep., 2018. Paper doi abstract bibtex In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.
@InProceedings{8553106,
author = {K. Choi and G. Fazekas and M. Sandler and K. Cho},
booktitle = {2018 26th European Signal Processing Conference (EUSIPCO)},
title = {A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging},
year = {2018},
pages = {1870-1874},
abstract = {In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.},
keywords = {music;neural nets;time-frequency analysis;transfer functions;input preprocessing techniques;time-frequency representations;frequency weighting;logarithmic magnitude compression;comprehensive experiments;audio preprocessing;music tagging;deep neural networks;audio signal preprocessing methods;Training;Time-frequency analysis;Neural networks;Kernel;Standards;Europe;Tagging},
doi = {10.23919/EUSIPCO.2018.8553106},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570434062.pdf},
}
Downloads: 0
{"_id":"9wbswyy8vmBc4w5y3","bibbaseid":"choi-fazekas-sandler-cho-acomparisonofaudiosignalpreprocessingmethodsfordeepneuralnetworksonmusictagging-2018","authorIDs":[],"author_short":["Choi, K.","Fazekas, G.","Sandler, M.","Cho, K."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["K."],"propositions":[],"lastnames":["Choi"],"suffixes":[]},{"firstnames":["G."],"propositions":[],"lastnames":["Fazekas"],"suffixes":[]},{"firstnames":["M."],"propositions":[],"lastnames":["Sandler"],"suffixes":[]},{"firstnames":["K."],"propositions":[],"lastnames":["Cho"],"suffixes":[]}],"booktitle":"2018 26th European Signal Processing Conference (EUSIPCO)","title":"A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging","year":"2018","pages":"1870-1874","abstract":"In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.","keywords":"music;neural nets;time-frequency analysis;transfer functions;input preprocessing techniques;time-frequency representations;frequency weighting;logarithmic magnitude compression;comprehensive experiments;audio preprocessing;music tagging;deep neural networks;audio signal preprocessing methods;Training;Time-frequency analysis;Neural networks;Kernel;Standards;Europe;Tagging","doi":"10.23919/EUSIPCO.2018.8553106","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570434062.pdf","bibtex":"@InProceedings{8553106,\n author = {K. Choi and G. Fazekas and M. Sandler and K. Cho},\n booktitle = {2018 26th European Signal Processing Conference (EUSIPCO)},\n title = {A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging},\n year = {2018},\n pages = {1870-1874},\n abstract = {In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.},\n keywords = {music;neural nets;time-frequency analysis;transfer functions;input preprocessing techniques;time-frequency representations;frequency weighting;logarithmic magnitude compression;comprehensive experiments;audio preprocessing;music tagging;deep neural networks;audio signal preprocessing methods;Training;Time-frequency analysis;Neural networks;Kernel;Standards;Europe;Tagging},\n doi = {10.23919/EUSIPCO.2018.8553106},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570434062.pdf},\n}\n\n","author_short":["Choi, K.","Fazekas, G.","Sandler, M.","Cho, K."],"key":"8553106","id":"8553106","bibbaseid":"choi-fazekas-sandler-cho-acomparisonofaudiosignalpreprocessingmethodsfordeepneuralnetworksonmusictagging-2018","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2018/papers/1570434062.pdf"},"keyword":["music;neural nets;time-frequency analysis;transfer functions;input preprocessing techniques;time-frequency representations;frequency weighting;logarithmic magnitude compression;comprehensive experiments;audio preprocessing;music tagging;deep neural networks;audio signal preprocessing methods;Training;Time-frequency analysis;Neural networks;Kernel;Standards;Europe;Tagging"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2018url.bib","creationDate":"2021-02-13T15:38:40.126Z","downloads":0,"keywords":["music;neural nets;time-frequency analysis;transfer functions;input preprocessing techniques;time-frequency representations;frequency weighting;logarithmic magnitude compression;comprehensive experiments;audio preprocessing;music tagging;deep neural networks;audio signal preprocessing methods;training;time-frequency analysis;neural networks;kernel;standards;europe;tagging"],"search_terms":["comparison","audio","signal","preprocessing","methods","deep","neural","networks","music","tagging","choi","fazekas","sandler","cho"],"title":"A Comparison of Audio Signal Preprocessing Methods for Deep Neural Networks on Music Tagging","year":2018,"dataSources":["yiZioZximP7hphDpY","iuBeKSmaES2fHcEE9"]}