An improved multipitch tracking algorithm with empirical mode decomposition

Wei Jiang, Wen Ju Liu*, Ying Wei Tan, Shan Liang

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

Multipitch tracking is beneficial for speech separation, audio transcription and many other tasks. In this paper, we greatly improve a state-of-the-art multipitch tracking algorithm. While the amplitude and individual peak positions of autocorrelation function (ACF) were used in previous algorithms, a novel feature based on the average frequency of each time-frequency (T-F) unit is proposed in this paper. This feature is computed by an empirical mode decomposition (EMD) method. Then it is utilized to form the conditional probabilities in the hidden Markov model (HMM) given a pitch state of each frame, and finally the most likely state sequence is searched out. Quantitative evaluations show that the novel feature is more effective, and our algorithm significantly outperforms the previous one.

Original languageEnglish
Title of host publicationPattern Recognition - 6th Chinese Conference, CCPR 2014, Proceedings
EditorsShutao Li, Yaonan Wang, Chenglin Liu
PublisherSpringer Verlag
Pages209-217
Number of pages9
ISBN (Electronic)9783662456422
DOIs
Publication statusPublished - 2014
Externally publishedYes
Event6th Chinese Conference on Pattern Recognition, CCPR 2014 - Changsha, China
Duration: 17 Nov 201419 Nov 2014

Publication series

NameCommunications in Computer and Information Science
Volume484
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference6th Chinese Conference on Pattern Recognition, CCPR 2014
Country/TerritoryChina
CityChangsha
Period17/11/1419/11/14

Keywords

  • Empirical mode decomposition
  • HMM tracking
  • Instantaneous frequency
  • Multipitch determination algorithm

Fingerprint

Dive into the research topics of 'An improved multipitch tracking algorithm with empirical mode decomposition'. Together they form a unique fingerprint.

Cite this