Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

An Approach for Calculation of a Feature Vector for Audio Fingerprinting Techniques

Mansurov Alexander Valerievich  (Ph.D. in Technical Sciences, Assistant Professor, Altai State University)

Ladygin Pavel Sergeevich  (Lecturer, Altai State University)

Audio fingerprinting is the essential technique for automatic music identification and monitoring for unauthorized use of music content. The complexity of audio fingerprinting techniques lies in providing the identification tokens with enough discriminative power, distortion invariance, and computational simplicity. The most complex step is retrieving the discriminative features (or feature vectors) from the processed audio file. In this paper, an approach for calculation of a feature vector based on musical notation of a musical composition is proposed. The detailed description of the proposed technique and testing results on simple and complex music pieces are presented. The proposed approach seems to be insensitive to various alterations of musical compositions.

Keywords:audio fingerprinting, audio files, spectrogram, identification
 

Read the full article …

Citation link:
Mansurov A. V., Ladygin P. S. An Approach for Calculation of a Feature Vector for Audio Fingerprinting Techniques // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2017. -№09. -С. 27-34
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences