Using Mel-Frequency Cepstral Coefficients in Missing Data Technique
<p/> <p>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 marginali...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2004-01-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1155/S1110865704309030 |
| _version_ | 1818540999581892608 |
|---|---|
| author | Gang Wei Jun Zhang Kwong Sam Hong Qingyang |
| author_facet | Gang Wei Jun Zhang Kwong Sam Hong Qingyang |
| author_sort | Gang Wei |
| collection | DOAJ |
| description | <p/> <p>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.</p> |
| first_indexed | 2024-12-11T22:02:47Z |
| format | Article |
| id | doaj.art-4069f09d541946e58991ca709a13df25 |
| institution | Directory Open Access Journal |
| issn | 1687-6172 1687-6180 |
| language | English |
| last_indexed | 2024-12-11T22:02:47Z |
| publishDate | 2004-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-4069f09d541946e58991ca709a13df252022-12-22T00:49:03ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802004-01-0120043652167Using Mel-Frequency Cepstral Coefficients in Missing Data TechniqueGang WeiJun ZhangKwong SamHong Qingyang<p/> <p>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.</p>http://dx.doi.org/10.1155/S1110865704309030MFCCmissing data techniquesrobust speech recognition |
| spellingShingle | Gang Wei Jun Zhang Kwong Sam Hong Qingyang Using Mel-Frequency Cepstral Coefficients in Missing Data Technique EURASIP Journal on Advances in Signal Processing MFCC missing data techniques robust speech recognition |
| title | Using Mel-Frequency Cepstral Coefficients in Missing Data Technique |
| title_full | Using Mel-Frequency Cepstral Coefficients in Missing Data Technique |
| title_fullStr | Using Mel-Frequency Cepstral Coefficients in Missing Data Technique |
| title_full_unstemmed | Using Mel-Frequency Cepstral Coefficients in Missing Data Technique |
| title_short | Using Mel-Frequency Cepstral Coefficients in Missing Data Technique |
| title_sort | using mel frequency cepstral coefficients in missing data technique |
| topic | MFCC missing data techniques robust speech recognition |
| url | http://dx.doi.org/10.1155/S1110865704309030 |
| work_keys_str_mv | AT gangwei usingmelfrequencycepstralcoefficientsinmissingdatatechnique AT junzhang usingmelfrequencycepstralcoefficientsinmissingdatatechnique AT kwongsam usingmelfrequencycepstralcoefficientsinmissingdatatechnique AT hongqingyang usingmelfrequencycepstralcoefficientsinmissingdatatechnique |