This paper introduces an algorithm for time-scale modification of audio signals based on using non-negative matrix factorization. The activation signals attributed to the detected components are used for identifying sound events. The segmentation of these events is used for detecting and preserving transients. In addition, the algorithm introduces the possibility of preserving the envelopes of overlapping sound events while globally modifying the duration of an audio clip.
|Title of host publication||Proceedings of the 22nd International Conference on Digital Audio Effects|
|Place of Publication||Birmingham|
|Publisher||Digital Audio Effects|
|Number of pages||6|
|Publication status||Published - 2 Sep 2019|
|Event||22nd International Conference on Digital Audio Effects - Birmingham City University, Birmingham, United Kingdom|
Duration: 2 Sep 2019 → 6 Sep 2019
Conference number: 22
|Name||DAFx Proceedings Series|
|Conference||22nd International Conference on Digital Audio Effects|
|Abbreviated title||DAFx 2019|
|Period||2/09/19 → 6/09/19|
Roma, G., Green, O., & Tremblay, P. A. (2019). Time Scale Modification of Audio Using Non-Negative Matrix Factorization. In Proceedings of the 22nd International Conference on Digital Audio Effects  (DAFx Proceedings Series; Vol. 2019). Birmingham: Digital Audio Effects.