Received 29.12.2016, Revised 02.03.2017, Accepted 05.04.2017

Information technology for searching audio recordings based on audio content

Oleksandr Tkachenko, Oksana Hrijo Tukalo

The information technology for search of the audio recording by an audio fragment in the audio archive is developed, which is based on the audio content search. The model of audio corpus, containing an array of audiofiles, a database of parameters and metadata, dynamic kd-tree, is proposed, which has reduced the duration of the selected audio fragment to search. There are suggested the new estimations of the measure proximity that take into account the specifics of the kd-tree use to find the nearest vector. Proposed search methods of audio allowed to achieve a significant reduction in the search time preserving its recall and precision

an automatic audio search by audio fragment, an approximate kd-tree search of the nearest vector, archive of audio recordings, cluster analysis, mel-frequency cepstral coefficients
37-40
Tkachenko, O., & Hrijo Tukalo, O. (2017). Information technology for searching audio recordings based on audio content. Information Technologies and Computer Engineering, 14(1), 37-40.

References

References in the process of publication