Using Mel-Frequency Cepstral Coefficients in Missing Data Technique

Jun ZHANG*, Sam KWONG, Gang WEI, Qingyang HONG

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

15 Citations (Scopus)


Filter bank is the most common feature being employed in the research of the marginalisation approaches for robust speech recognition due to its simplicity in detecting the unreliable data in the frequency domain. In this paper, we propose a hybrid approach based on the marginalisation and the soft decision techniques that make use of the Mel-frequency cepstral coefficients (MFCCs) instead of filter bank coefficients. A new technique for estimating the reliability of each cepstral component is also presented. Experimental results show the effectiveness of the proposed approaches.

Original languageEnglish
Article number652167
Pages (from-to)340-346
Number of pages7
JournalEurasip Journal on Applied Signal Processing
Issue number3
Early online date21 Mar 2004
Publication statusPublished - Mar 2004
Externally publishedYes


  • MFCC
  • Missing data techniques
  • Robust speech recognition


Dive into the research topics of 'Using Mel-Frequency Cepstral Coefficients in Missing Data Technique'. Together they form a unique fingerprint.

Cite this