The proposed method is inspired by ideas from Computational Auditory Scene Analysis. We formulate singing voice tracking and formation as a graph partitioning problem and solve it using the normalized cut which is a global criterion for segmenting graphs that has been used in Computer Vision.
This work aim at creating a large digital archive of killer whale or orca vocalizations. The goal of the project is to digitize approximately 20000 hours of existing analog recordings of these vocalizations in order to facilitate access to researchers internationally. We are also developing tools to assist content-based access and retrieval over this large digital audio archive
In this study, the autoregressive (AR) modeling of the amplitude and frequency parameters of sinusoidal components allows us to interpolate realistically missing audio data, especially in the case of musical modulations such as vibrato or tremolo.
The robust estimation of the frequency of some sinusoidal components is a major prerequisite for many applications, such as in sinusoidal sound modeling, where the estimation has to be done with a low complexity, on short-term spectra.