An efficient voice transcription scheme for music retrieval

Byeong Jun Han, Seungmin Rho, Eenjun Hwan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In this paper, we propose a new scheme for transcribing sung or hummed queries into a sequence of pitch and duration pairs automatically for efficient music retrieval. More specifically, we present two novel methods called WAE (Windowed Average Energy) and dynamic threshold method for ADF onsets for note segmentation and onset/offset detection in acoustic signal, respectively. The former improves previous energy-based approaches such as AE by defining small but coherent windows with local and global threshold values. The latter also improves the traditional global/local threshold method. By performing various experiments on our prototype music retrieval system, we show the effectiveness of our proposed scheme.

Original languageEnglish
Title of host publicationProceedings - 2007 International Conference on Multimedia and Ubiquitous Engineering, MUE 2007
Pages366-371
Number of pages6
DOIs
Publication statusPublished - 2007
Event2007 International Conference on Multimedia and Ubiquitous Engineering, MUE 2007 - Seoul, Korea, Republic of
Duration: 2007 Apr 262007 Apr 28

Publication series

NameProceedings - 2007 International Conference on Multimedia and Ubiquitous Engineering, MUE 2007

Other

Other2007 International Conference on Multimedia and Ubiquitous Engineering, MUE 2007
CountryKorea, Republic of
CitySeoul
Period07/4/2607/4/28

ASJC Scopus subject areas

  • Software
  • Media Technology

Fingerprint Dive into the research topics of 'An efficient voice transcription scheme for music retrieval'. Together they form a unique fingerprint.

Cite this