Smart-Median: A New Real-Time Algorithm for Smoothing Singing Pitch Contours

Smart-Median: A New Real-Time Algorithm for Smoothing Singing Pitch Contours. Faghih, B. & Timoney, J. Applied Sciences, 12(14):7026, July, 2022.

Paper doi abstract bibtex 2 downloads

Pitch detection is usually one of the fundamental steps in audio signal processing. However, it is common for pitch detectors to estimate a portion of the fundamental frequencies incorrectly, especially in real-time environments and when applied to singing. Therefore, the estimated pitch contour usually has errors. To remove these errors, a contour smoother algorithm should be employed. However, because none of the current contour-smoother algorithms has been explicitly designed to be applied to contours generated from singing, they are often unsuitable for this purpose. Therefore, this article aims to introduce a new smoother algorithm that rectiﬁes this. The proposed smoother algorithm is compared with 15 other smoother algorithms over approximately 2700 pitch contours. Four metrics were used for the comparison. According to all the metrics, the proposed algorithm could smooth the contours more accurately than other algorithms. A distinct conclusion is that smoother algorithms should be designed according to the contour type and the result's ﬁnal applications.

@Article{          faghih.ea2022-smart-median,
    author       = {Faghih, Behnam and Timoney, Joseph},
    year         = {2022},
    title        = {Smart-{Median}: {A} {New} {Real}-{Time} {Algorithm} for
                   {Smoothing} {Singing} {Pitch} {Contours}},
    volume       = {12},
    issn         = {2076-3417},
    shorttitle   = {Smart-{Median}},
    url          = {https://www.mdpi.com/2076-3417/12/14/7026},
    doi          = {10.3390/app12147026},
    abstract     = {Pitch detection is usually one of the fundamental steps
                   in audio signal processing. However, it is common for
                   pitch detectors to estimate a portion of the fundamental
                   frequencies incorrectly, especially in real-time
                   environments and when applied to singing. Therefore, the
                   estimated pitch contour usually has errors. To remove
                   these errors, a contour smoother algorithm should be
                   employed. However, because none of the current
                   contour-smoother algorithms has been explicitly designed
                   to be applied to contours generated from singing, they are
                   often unsuitable for this purpose. Therefore, this article
                   aims to introduce a new smoother algorithm that rectiﬁes
                   this. The proposed smoother algorithm is compared with 15
                   other smoother algorithms over approximately 2700 pitch
                   contours. Four metrics were used for the comparison.
                   According to all the metrics, the proposed algorithm could
                   smooth the contours more accurately than other algorithms.
                   A distinct conclusion is that smoother algorithms should
                   be designed according to the contour type and the result's
                   ﬁnal applications.},
    language     = {en},
    number       = {14},
    urldate      = {2022-07-13},
    journal      = {Applied Sciences},
    month        = jul,
    keywords     = {music contour},
    pages        = {7026}
}

Downloads: 2

{"_id":"2P4KMLAPrXYJYoWgv","bibbaseid":"faghih-timoney-smartmediananewrealtimealgorithmforsmoothingsingingpitchcontours-2022","author_short":["Faghih, B.","Timoney, J."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Faghih"],"firstnames":["Behnam"],"suffixes":[]},{"propositions":[],"lastnames":["Timoney"],"firstnames":["Joseph"],"suffixes":[]}],"year":"2022","title":"Smart-Median: A New Real-Time Algorithm for Smoothing Singing Pitch Contours","volume":"12","issn":"2076-3417","shorttitle":"Smart-Median","url":"https://www.mdpi.com/2076-3417/12/14/7026","doi":"10.3390/app12147026","abstract":"Pitch detection is usually one of the fundamental steps in audio signal processing. However, it is common for pitch detectors to estimate a portion of the fundamental frequencies incorrectly, especially in real-time environments and when applied to singing. Therefore, the estimated pitch contour usually has errors. To remove these errors, a contour smoother algorithm should be employed. However, because none of the current contour-smoother algorithms has been explicitly designed to be applied to contours generated from singing, they are often unsuitable for this purpose. Therefore, this article aims to introduce a new smoother algorithm that rectiﬁes this. The proposed smoother algorithm is compared with 15 other smoother algorithms over approximately 2700 pitch contours. Four metrics were used for the comparison. According to all the metrics, the proposed algorithm could smooth the contours more accurately than other algorithms. A distinct conclusion is that smoother algorithms should be designed according to the contour type and the result's ﬁnal applications.","language":"en","number":"14","urldate":"2022-07-13","journal":"Applied Sciences","month":"July","keywords":"music contour","pages":"7026","bibtex":"@Article{ faghih.ea2022-smart-median,\n author = {Faghih, Behnam and Timoney, Joseph},\n year = {2022},\n title = {Smart-{Median}: {A} {New} {Real}-{Time} {Algorithm} for\n {Smoothing} {Singing} {Pitch} {Contours}},\n volume = {12},\n issn = {2076-3417},\n shorttitle = {Smart-{Median}},\n url = {https://www.mdpi.com/2076-3417/12/14/7026},\n doi = {10.3390/app12147026},\n abstract = {Pitch detection is usually one of the fundamental steps\n in audio signal processing. However, it is common for\n pitch detectors to estimate a portion of the fundamental\n frequencies incorrectly, especially in real-time\n environments and when applied to singing. Therefore, the\n estimated pitch contour usually has errors. To remove\n these errors, a contour smoother algorithm should be\n employed. However, because none of the current\n contour-smoother algorithms has been explicitly designed\n to be applied to contours generated from singing, they are\n often unsuitable for this purpose. Therefore, this article\n aims to introduce a new smoother algorithm that rectiﬁes\n this. The proposed smoother algorithm is compared with 15\n other smoother algorithms over approximately 2700 pitch\n contours. Four metrics were used for the comparison.\n According to all the metrics, the proposed algorithm could\n smooth the contours more accurately than other algorithms.\n A distinct conclusion is that smoother algorithms should\n be designed according to the contour type and the result's\n ﬁnal applications.},\n language = {en},\n number = {14},\n urldate = {2022-07-13},\n journal = {Applied Sciences},\n month = jul,\n keywords = {music contour},\n pages = {7026}\n}\n\n","author_short":["Faghih, B.","Timoney, J."],"key":"faghih.ea2022-smart-median","id":"faghih.ea2022-smart-median","bibbaseid":"faghih-timoney-smartmediananewrealtimealgorithmforsmoothingsingingpitchcontours-2022","role":"author","urls":{"Paper":"https://www.mdpi.com/2076-3417/12/14/7026"},"keyword":["music contour"],"metadata":{"authorlinks":{}},"downloads":2},"bibtype":"article","biburl":"https://hmb.sampaio.me/bibliografia.bib.txt","dataSources":["n6MFY2CscQLDpJ7nT"],"keywords":["music contour"],"search_terms":["smart","median","new","real","time","algorithm","smoothing","singing","pitch","contours","faghih","timoney"],"title":"Smart-Median: A New Real-Time Algorithm for Smoothing Singing Pitch Contours","year":2022,"downloads":2}