In this paper, a new type of metric that defines the similarity between musical audio signals is proposed. Based on the spectral flatness criterion, those metrics achieve low co...
The research presented in this paper is focused on global tempo transformations of music performances. We are investigating the problem of how a performance played at a particular...
Abstract Trained musicians intuitively produce expressive variations that add to their audience's enjoyment. However, there is little quantitative information about the kinds ...
In this paper, we present an algorithm for time-scale modification of music signals, based on the waveform similarity overlap-and-add technique (WSOLA). A well-known disadvantage o...
Extracting a singing voice from its music accompaniment can significantly facilitate certain applications of Music Information Retrieval including singer identification and singin...
Stratis Sofianos, Aladdin M. Ariyaeeinia, Richard ...