Bayesian suppression of memoryless nonlinear audio distortion. Carvalho, H. T., Ávila, F. R., & Biscainho, L. W. P. In *2015 23rd European Signal Processing Conference (EUSIPCO)*, pages 1058-1062, Aug, 2015.

Paper doi abstract bibtex

Paper doi abstract bibtex

Even if nonlinear distortion may be deliberately applied to audio signals for esthetic or technical reasons, it is common to hear annoying defects in accidentally saturated or amateurishly processed audio - which calls for some means to automatically undo the impairment. This paper proposes an algorithm to blindly identify the nonlinear distortion suffered by an audio signal and reconstruct its original form. Designed to deal with memoryless impairments, the model adopted for the nonlinear distortion is a curve composed of an invertible sequence of linear segments, capable of following the typical shape of compressed audio, and whose parameters are easily interpretable and thus constrainable. The solution builds on the posterior statistical distribution of the curve parameters given the degraded signal, and yields perceptually impressive results for real signals distorted by arbitrary curves.

@InProceedings{7362545, author = {H. T. Carvalho and F. R. Ávila and L. W. P. Biscainho}, booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)}, title = {Bayesian suppression of memoryless nonlinear audio distortion}, year = {2015}, pages = {1058-1062}, abstract = {Even if nonlinear distortion may be deliberately applied to audio signals for esthetic or technical reasons, it is common to hear annoying defects in accidentally saturated or amateurishly processed audio - which calls for some means to automatically undo the impairment. This paper proposes an algorithm to blindly identify the nonlinear distortion suffered by an audio signal and reconstruct its original form. Designed to deal with memoryless impairments, the model adopted for the nonlinear distortion is a curve composed of an invertible sequence of linear segments, capable of following the typical shape of compressed audio, and whose parameters are easily interpretable and thus constrainable. The solution builds on the posterior statistical distribution of the curve parameters given the degraded signal, and yields perceptually impressive results for real signals distorted by arbitrary curves.}, keywords = {audio signal processing;Bayes methods;compressed sensing;nonlinear distortion;signal reconstruction;statistical distributions;Bayesian suppression;memoryless nonlinear audio distortion;audio signals;nonlinear distortion;linear segments;compressed audio;statistical distribution;Nonlinear distortion;Signal processing algorithms;Europe;Shape;White noise;Nonlinear distortion;Bayesian signal processing;blind system identification;audio processing}, doi = {10.1109/EUSIPCO.2015.7362545}, issn = {2076-1465}, month = {Aug}, url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570103841.pdf}, }

Downloads: 0

{"_id":"92uP3x7thk6yvjoM2","bibbaseid":"carvalho-vila-biscainho-bayesiansuppressionofmemorylessnonlinearaudiodistortion-2015","authorIDs":[],"author_short":["Carvalho, H. T.","Ávila, F. R.","Biscainho, L. W. P."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["H.","T."],"propositions":[],"lastnames":["Carvalho"],"suffixes":[]},{"firstnames":["F.","R."],"propositions":[],"lastnames":["Ávila"],"suffixes":[]},{"firstnames":["L.","W.","P."],"propositions":[],"lastnames":["Biscainho"],"suffixes":[]}],"booktitle":"2015 23rd European Signal Processing Conference (EUSIPCO)","title":"Bayesian suppression of memoryless nonlinear audio distortion","year":"2015","pages":"1058-1062","abstract":"Even if nonlinear distortion may be deliberately applied to audio signals for esthetic or technical reasons, it is common to hear annoying defects in accidentally saturated or amateurishly processed audio - which calls for some means to automatically undo the impairment. This paper proposes an algorithm to blindly identify the nonlinear distortion suffered by an audio signal and reconstruct its original form. Designed to deal with memoryless impairments, the model adopted for the nonlinear distortion is a curve composed of an invertible sequence of linear segments, capable of following the typical shape of compressed audio, and whose parameters are easily interpretable and thus constrainable. The solution builds on the posterior statistical distribution of the curve parameters given the degraded signal, and yields perceptually impressive results for real signals distorted by arbitrary curves.","keywords":"audio signal processing;Bayes methods;compressed sensing;nonlinear distortion;signal reconstruction;statistical distributions;Bayesian suppression;memoryless nonlinear audio distortion;audio signals;nonlinear distortion;linear segments;compressed audio;statistical distribution;Nonlinear distortion;Signal processing algorithms;Europe;Shape;White noise;Nonlinear distortion;Bayesian signal processing;blind system identification;audio processing","doi":"10.1109/EUSIPCO.2015.7362545","issn":"2076-1465","month":"Aug","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570103841.pdf","bibtex":"@InProceedings{7362545,\n author = {H. T. Carvalho and F. R. Ávila and L. W. P. Biscainho},\n booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},\n title = {Bayesian suppression of memoryless nonlinear audio distortion},\n year = {2015},\n pages = {1058-1062},\n abstract = {Even if nonlinear distortion may be deliberately applied to audio signals for esthetic or technical reasons, it is common to hear annoying defects in accidentally saturated or amateurishly processed audio - which calls for some means to automatically undo the impairment. This paper proposes an algorithm to blindly identify the nonlinear distortion suffered by an audio signal and reconstruct its original form. Designed to deal with memoryless impairments, the model adopted for the nonlinear distortion is a curve composed of an invertible sequence of linear segments, capable of following the typical shape of compressed audio, and whose parameters are easily interpretable and thus constrainable. The solution builds on the posterior statistical distribution of the curve parameters given the degraded signal, and yields perceptually impressive results for real signals distorted by arbitrary curves.},\n keywords = {audio signal processing;Bayes methods;compressed sensing;nonlinear distortion;signal reconstruction;statistical distributions;Bayesian suppression;memoryless nonlinear audio distortion;audio signals;nonlinear distortion;linear segments;compressed audio;statistical distribution;Nonlinear distortion;Signal processing algorithms;Europe;Shape;White noise;Nonlinear distortion;Bayesian signal processing;blind system identification;audio processing},\n doi = {10.1109/EUSIPCO.2015.7362545},\n issn = {2076-1465},\n month = {Aug},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570103841.pdf},\n}\n\n","author_short":["Carvalho, H. T.","Ávila, F. R.","Biscainho, L. W. P."],"key":"7362545","id":"7362545","bibbaseid":"carvalho-vila-biscainho-bayesiansuppressionofmemorylessnonlinearaudiodistortion-2015","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570103841.pdf"},"keyword":["audio signal processing;Bayes methods;compressed sensing;nonlinear distortion;signal reconstruction;statistical distributions;Bayesian suppression;memoryless nonlinear audio distortion;audio signals;nonlinear distortion;linear segments;compressed audio;statistical distribution;Nonlinear distortion;Signal processing algorithms;Europe;Shape;White noise;Nonlinear distortion;Bayesian signal processing;blind system identification;audio processing"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2015url.bib","creationDate":"2021-02-13T17:31:52.387Z","downloads":0,"keywords":["audio signal processing;bayes methods;compressed sensing;nonlinear distortion;signal reconstruction;statistical distributions;bayesian suppression;memoryless nonlinear audio distortion;audio signals;nonlinear distortion;linear segments;compressed audio;statistical distribution;nonlinear distortion;signal processing algorithms;europe;shape;white noise;nonlinear distortion;bayesian signal processing;blind system identification;audio processing"],"search_terms":["bayesian","suppression","memoryless","nonlinear","audio","distortion","carvalho","ávila","biscainho"],"title":"Bayesian suppression of memoryless nonlinear audio distortion","year":2015,"dataSources":["eov4vbT6mnAiTpKji","knrZsDjSNHWtA9WNT"]}