A Comparative Study of Pitch Extraction Algorithms on a Large Variety of Singing Sounds
This study addresses the problem of accurate pitch extraction for singing voice analysis, which is important for researchers and practitioners in music technology and audio processing, but it is incremental as it focuses on adapting existing methods rather than introducing new ones.
The paper tackled the adaptation of pitch tracking techniques from speech to singing voice analysis by conducting a comparative evaluation of state-of-the-art algorithms on a large annotated database of singing sounds, assessing performance in voicing boundary detection, pitch contour accuracy, and robustness to reverberation.
The problem of pitch tracking has been extensively studied in the speech research community. The goal of this paper is to investigate how these techniques should be adapted to singing voice analysis, and to provide a comparative evaluation of the most representative state-of-the-art approaches. This study is carried out on a large database of annotated singing sounds with aligned EGG recordings, comprising a variety of singer categories and singing exercises. The algorithmic performance is assessed according to the ability to detect voicing boundaries and to accurately estimate pitch contour. First, we evaluate the usefulness of adapting existing methods to singing voice analysis. Then we compare the accuracy of several pitch-extraction algorithms, depending on singer category and laryngeal mechanism. Finally, we analyze their robustness to reverberation.