Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine
This paper proposes support vector machine (SVM) based voice activity detection using FuzzyEn to improve detection performance under noisy conditions. The proposed voice activity detection (VAD) uses fuzzy entropy (FuzzyEn) as a feature extracted from noise-reduced speech signals to train an SVM mod...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-08-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1099-4300/18/8/298 |
| _version_ | 1828120043519475712 |
|---|---|
| author | R. Johny Elton P. Vasuki J. Mohanalin |
| author_facet | R. Johny Elton P. Vasuki J. Mohanalin |
| author_sort | R. Johny Elton |
| collection | DOAJ |
| description | This paper proposes support vector machine (SVM) based voice activity detection using FuzzyEn to improve detection performance under noisy conditions. The proposed voice activity detection (VAD) uses fuzzy entropy (FuzzyEn) as a feature extracted from noise-reduced speech signals to train an SVM model for speech/non-speech classification. The proposed VAD method was tested by conducting various experiments by adding real background noises of different signal-to-noise ratios (SNR) ranging from −10 dB to 10 dB to actual speech signals collected from the TIMIT database. The analysis proves that FuzzyEn feature shows better results in discriminating noise and corrupted noisy speech. The efficacy of the SVM classifier was validated using 10-fold cross validation. Furthermore, the results obtained by the proposed method was compared with those of previous standardized VAD algorithms as well as recently developed methods. Performance comparison suggests that the proposed method is proven to be more efficient in detecting speech under various noisy environments with an accuracy of 93.29%, and the FuzzyEn feature detects speech efficiently even at low SNR levels. |
| first_indexed | 2024-04-11T13:58:52Z |
| format | Article |
| id | doaj.art-0e558434327b470ab1e9132d88c9a414 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-11T13:58:52Z |
| publishDate | 2016-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-0e558434327b470ab1e9132d88c9a4142022-12-22T04:20:10ZengMDPI AGEntropy1099-43002016-08-0118829810.3390/e18080298e18080298Voice Activity Detection Using Fuzzy Entropy and Support Vector MachineR. Johny Elton0P. Vasuki1J. Mohanalin2Department of Electronics and Communication Engineering, K.L.N. College of Information Technology, Madurai 630612, IndiaDepartment of Electronics and Communication Engineering, K.L.N. College of Information Technology, Madurai 630612, IndiaDepartment of Electrical and Electronics Engineering, College of Engineering Pathanapuram, Kerala 689696, IndiaThis paper proposes support vector machine (SVM) based voice activity detection using FuzzyEn to improve detection performance under noisy conditions. The proposed voice activity detection (VAD) uses fuzzy entropy (FuzzyEn) as a feature extracted from noise-reduced speech signals to train an SVM model for speech/non-speech classification. The proposed VAD method was tested by conducting various experiments by adding real background noises of different signal-to-noise ratios (SNR) ranging from −10 dB to 10 dB to actual speech signals collected from the TIMIT database. The analysis proves that FuzzyEn feature shows better results in discriminating noise and corrupted noisy speech. The efficacy of the SVM classifier was validated using 10-fold cross validation. Furthermore, the results obtained by the proposed method was compared with those of previous standardized VAD algorithms as well as recently developed methods. Performance comparison suggests that the proposed method is proven to be more efficient in detecting speech under various noisy environments with an accuracy of 93.29%, and the FuzzyEn feature detects speech efficiently even at low SNR levels.http://www.mdpi.com/1099-4300/18/8/298voice activity detectionfuzzy entropysupport vector machinek-NN |
| spellingShingle | R. Johny Elton P. Vasuki J. Mohanalin Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine Entropy voice activity detection fuzzy entropy support vector machine k-NN |
| title | Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine |
| title_full | Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine |
| title_fullStr | Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine |
| title_full_unstemmed | Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine |
| title_short | Voice Activity Detection Using Fuzzy Entropy and Support Vector Machine |
| title_sort | voice activity detection using fuzzy entropy and support vector machine |
| topic | voice activity detection fuzzy entropy support vector machine k-NN |
| url | http://www.mdpi.com/1099-4300/18/8/298 |
| work_keys_str_mv | AT rjohnyelton voiceactivitydetectionusingfuzzyentropyandsupportvectormachine AT pvasuki voiceactivitydetectionusingfuzzyentropyandsupportvectormachine AT jmohanalin voiceactivitydetectionusingfuzzyentropyandsupportvectormachine |