A simple algorithm of pitch detection by using fast direct transform

Yuuki Yazama, Yasue Mitsukura, Minoru Fukumi, Norio Akamatsu

Research output: Contribution to conferencePaper

Abstract

There are some fundamental frequency detection methods for speech processing such as cepstrum analysis. However, the traditional methods need a lot of computing time and arithmetic processing. Moreover, a speech signal is converted into frequency domain by using an analysis section. In this paper, we propose a fast direct transformation (FDT). FDT extracts an amplitude feature of a signal by a simple computation. We perform the fundamental frequency detection of speech signal by using FDT. We compare the FDT algorithm with the conventional fundamental frequency detection methods by using teacher data(fundamental frequency) detected by the inspection. We perform an improvement as compared with a autocorrelation method by using FDT algorithm.

Original languageEnglish
Pages205-209
Number of pages5
Publication statusPublished - 2005 Dec 12
Event2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005 - Espoo, Finland
Duration: 2005 Jun 272005 Jun 30

Other

Other2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005
CountryFinland
CityEspoo
Period05/6/2705/6/30

Keywords

  • Fast direct transform
  • Pitch detection algorithm
  • Speech processing

ASJC Scopus subject areas

  • Computational Mathematics

Fingerprint Dive into the research topics of 'A simple algorithm of pitch detection by using fast direct transform'. Together they form a unique fingerprint.

  • Cite this

    Yazama, Y., Mitsukura, Y., Fukumi, M., & Akamatsu, N. (2005). A simple algorithm of pitch detection by using fast direct transform. 205-209. Paper presented at 2005 IEEE International Symposium on Computational Intelligence in Robotics and Automation CIRA 2005, Espoo, Finland.