Multi-Time Segment Peak-based Audio Fingerprinting 


Vol. 14,  No. 1, pp. 48-52, Jan.  2025
https://doi.org/10.3745/TKIPS.2025.14.1.48


PDF
  Abstract

This paper explores methods to enhance the accuracy of audio fingerprinting technology. Since the early 2010s, audio fingerprinting has been actively researched for applications such as music and media retrieval. More recently, advancements in deep learning have spurred efforts to improve the accuracy of this technology. In this study, we propose an approach to enhance audio fingerprinting accuracy by introducing specific steps and techniques into the process. The first step involves detecting key peaks and generating audio fingerprints. This approach simplifies computational processes and achieves robust signal recognition even in noisy environments by leveraging the intensity of prominent frequency peaks. The second step involves generating audio fingerprints based on multi-time segment peaks. By extracting peaks from different audio segments, this method creates fingerprints that comprehensively reflect the characteristics of various temporal sections. This approach captures the temporal features of the audio in greater detail by incorporating segments of varying lengths. Comparative analysis reveals that while the proposed method maintains a similar processing time to conventional approaches, it delivers significantly higher accuracy.

  Statistics
  Cite this article

[IEEE Style]

S. U. Hyun and J. Heo, "Multi-Time Segment Peak-based Audio Fingerprinting," The Transactions of the Korea Information Processing Society, vol. 14, no. 1, pp. 48-52, 2025. DOI: https://doi.org/10.3745/TKIPS.2025.14.1.48.

[ACM Style]

Son U Hyun and Junyoung Heo. 2025. Multi-Time Segment Peak-based Audio Fingerprinting. The Transactions of the Korea Information Processing Society, 14, 1, (2025), 48-52. DOI: https://doi.org/10.3745/TKIPS.2025.14.1.48.

Forms

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

Old Journals

Indexing

All publications of TKIPS is indexed in DOI, EBSCO, Google Scholar, Crossref, and CrossCheck.

TKIPS is also selected as the Journal for Accreditation by NRF (National Research Foundation of Korea).

Related Journals