Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.V.

Sony Corporation

Michael Saupe

Markus Cremer

Markus Van Pinxteren

For grouping temporal segments of an audio piece, which is structured into main parts repeatedly occurring in the audio piece, into various segment classes, at first a similarity representation for the segments is provided, wherein the similarity representation for each segment comprises an associated plurality of similarity values, wherein the similarity values indicate how similar the segment is to every other segment of the audio piece. Hereupon, using the similarity values associated with the segment, a similarity threshold value for a segment is calculated in order to then associate a segment with a segment class when the similarity value of the segment meets a predetermined relation with reference to the similarity threshold value. With this, clustering is achieved, which also works efficiently and correctly where there are segments with strongly different or almost equal combined similarity values.

Apparatus and method for grouping temporal segments of a piece of music

For the segment class designation the temporal position of segments in two candidate segment classes is used for the stanza/refrain selection by means of a segment class designation means, wherein the highest-order segment class is designated as refrain segment class only when it has a segment following temporally later in the audio piece than the latest segment of the other candidate segment class. With this, segment class labeling with a low error rate is achieved, which can at the same time be implemented with easy effort and is further predestined for automated flow.

Apparatus and method for designating various segment classes

For changing a segmentation of an audio piece after a segment class assignment, at first a short segment is selected, which has a length shorter than a predetermined minimum length. This short segment is preferably merged with the corresponding successor segment or predecessor segment using information on a segment class membership of the short segment itself, but also the successor segment or the predecessor segment, in order to obtain a changed segmentation of the audio signal. With this, a not over-segmented segment representation of the audio signal is obtained, which further includes all audio information, i.e. is not a representation of the audio piece with holes.

Growing community of inventors

Ilmenau, Germany

Michael Saupe