A new method for pitch smoothing

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

“…However, as is discussed by Faghih and Timoney [5], a fixed distance from the ground truth may not be a good approach, because the perceptual effect of 16 Hz is different when the estimated pitch is 100 Hz compared to 1000 Hz. However, it is also common to use a percentage, usually 20%, as the threshold [20], and a similar approach is used in this study.…”

“…This technique was presented by Jlassi et al [20]. This approach has two main steps, first, finding the incorrect points in the pitch contour by considering those that exhibit a difference of more than a set threshold from both their previous and successive points.…”

“…They have been applied to the smoothing of pitch contours, such as in the study by Kasi and Zahorian [18] that used the Median filter. However, there are certain adjusted versions of these algorithms for smoothing estimated pitches; for example, Okada et al [19] and Jlassi et al [20] introduced pitch contour algorithms based on the Median filter. In the following, some of these adjusted algorithms are discussed.…”

“…The smoothing approach presented by Jlassi et al [20] was designed for spoken English. Their smoothing system was based on the moving average filter.…”

Using Deep Neural Networks for Smoothing Pitch Profiles in Connected Speech

“…That is why in the literature we can find several studies aiming at proposing pitch profile smoothers that further post-process the PDAs output trying to enhance the profile correctness. Some works try to correct intonation profiles by applying traditional techniques (Zhao, O'Shaughnessy, and Minh-Quang 2007;So, Jia, and Cai 2012;Jlassi, Bouzid, and Ellouze 2016), while few others (see for example (Kellman and Morgan 2017;Han and Wang 2014)) are based on DNN (either Multi-Layer Perceptrons or Elman Recurrent Neural Networks).…”