An embedded system design for speech command recognition using improved AMDF-based pitch features

Shun Chieh Lin, Jhing Fa Wang, Jia Ching Wang, Chuan I. Tu

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

Abstract

This paper presents an embedded system design for speech command recognition using improved AMDF (Average Magnitude Difference Function)-based pitch features. Compared with the autocorrelation method, AMDF has the advantage of low computation and high precision. This work presents three kinds of improvement for AMDF-based pitch extraction. One is the circular AMDF (CAMDF), one is the modified AMDF (MAMDF), and the other is modified and circular AMDF (MCAMDF). With the mixed segment containing voiced and unvoiced speech, the CAMDF-based method can give the pitch period of the voiced part and improve the performance on pitch extraction. Besides, dynamic programming and its modifications have been successfully adopted for speech command recognizer. The experimental results show that the proposed design obtained a noticeable achievement and would be utilized for various command-driven speech interactive applications such as intelligent toys, hand-free remote controlling, machine learning, and speech retrieval, etc.

Original languageEnglish
Title of host publicationProceedings of the 2008 International Conference on Embedded Systems and Applications, ESA 2008
Pages88-92
Number of pages5
StatePublished - 2008
Event2008 International Conference on Embedded Systems and Applications, ESA 2008 - Las Vegas, NV, United States
Duration: 14 Jul 200817 Jul 2008

Publication series

NameProceedings of the 2008 International Conference on Embedded Systems and Applications, ESA 2008

Conference

Conference2008 International Conference on Embedded Systems and Applications, ESA 2008
Country/TerritoryUnited States
CityLas Vegas, NV
Period14/07/0817/07/08

Keywords

  • AMDF-based pitch extraction
  • And dynamic time warping
  • Embedded system design
  • Speech command recognition
  • Speech processing

Fingerprint

Dive into the research topics of 'An embedded system design for speech command recognition using improved AMDF-based pitch features'. Together they form a unique fingerprint.

Cite this