In this paper, to automatically generate musical thumbnails that contain the main part of the original tune, we propose a new estimation method for identifying structure changes i...
We present a study on purely data-based recognition of animal sounds, performing evaluation on a real-world database obtained from the Humboldt-University Animal Sound Archive. As...
Sound textures may be defined as sounds whose character depends on statistical properties as much as the specific details of each individually-perceived event. Recent work has d...
Daniel P. W. Ellis, Xiaohong Zeng, Josh H. McDermo...
Modern monaural voice and accompaniment separation systems usually consist of two main modules: melody extraction and timefrequency masking. A main distinction between different s...
This paper proposes a method recovering audio-visual synchronization of multimedia content. It exploits the correlation between the acoustic and the visual signals in order to est...