Hilbert spectrum based features for speech/music classification
Automatic Speech/Music classification uses different signal processing techniques to categorize multimedia content into different classes. The proposed work explores Hilbert Spectrum (HS) obtained from different AM-FM components of an audio signal, also called Intrinsic Mode Functions (IMFs...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Technical Sciences in Cacak
2022-01-01
|
| Series: | Serbian Journal of Electrical Engineering |
| Subjects: | |
| Online Access: | http://www.doiserbia.nb.rs/img/doi/1451-4869/2022/1451-48692202239K.pdf |
| _version_ | 1818160657087856640 |
|---|---|
| author | Kumar Arvind Solanki Sandeep Singh Chandra Mahesh |
| author_facet | Kumar Arvind Solanki Sandeep Singh Chandra Mahesh |
| author_sort | Kumar Arvind |
| collection | DOAJ |
| description | Automatic Speech/Music classification uses different signal processing
techniques to categorize multimedia content into different classes. The
proposed work explores Hilbert Spectrum (HS) obtained from different AM-FM
components of an audio signal, also called Intrinsic Mode Functions (IMFs)
to classify an incoming audio signal into speech/music signal. The HS is a
twodimensional representation of instantaneous energies (IE) and
instantaneous frequencies (IF) obtained using Hilbert Transform of the IMFs.
This HS is further processed using Mel-filter bank and Discrete Cosine
Transform (DCT) to generate novel IF and Instantaneous Amplitude (IA) based
cepstral features. Validations of the results were done using three
databases-Slaney Database, GTZAN and MUSAN database. To evaluate the
general applicability of the proposed features, extensive experiments were
conducted on different combination of audio files from S&S, GTZAN and MUSAN
database and promising results are achieved. Finally, performance of the
system is compared with performance of existing cepstral features and
previous works in this domain. |
| first_indexed | 2024-12-11T16:05:21Z |
| format | Article |
| id | doaj.art-1e5c9d4b097e410cade0037cdcc8ca8e |
| institution | Directory Open Access Journal |
| issn | 1451-4869 2217-7183 |
| language | English |
| last_indexed | 2024-12-11T16:05:21Z |
| publishDate | 2022-01-01 |
| publisher | Faculty of Technical Sciences in Cacak |
| record_format | Article |
| series | Serbian Journal of Electrical Engineering |
| spelling | doaj.art-1e5c9d4b097e410cade0037cdcc8ca8e2022-12-22T00:59:12ZengFaculty of Technical Sciences in CacakSerbian Journal of Electrical Engineering1451-48692217-71832022-01-0119223925910.2298/SJEE2202239K1451-48692202239KHilbert spectrum based features for speech/music classificationKumar Arvind0Solanki Sandeep Singh1Chandra Mahesh2Department of ECE, Birla Institute of Technology, Ranchi, IndiaDepartment of ECE, Birla Institute of Technology, Ranchi, IndiaDepartment of ECE, Reva University, BengaluruAutomatic Speech/Music classification uses different signal processing techniques to categorize multimedia content into different classes. The proposed work explores Hilbert Spectrum (HS) obtained from different AM-FM components of an audio signal, also called Intrinsic Mode Functions (IMFs) to classify an incoming audio signal into speech/music signal. The HS is a twodimensional representation of instantaneous energies (IE) and instantaneous frequencies (IF) obtained using Hilbert Transform of the IMFs. This HS is further processed using Mel-filter bank and Discrete Cosine Transform (DCT) to generate novel IF and Instantaneous Amplitude (IA) based cepstral features. Validations of the results were done using three databases-Slaney Database, GTZAN and MUSAN database. To evaluate the general applicability of the proposed features, extensive experiments were conducted on different combination of audio files from S&S, GTZAN and MUSAN database and promising results are achieved. Finally, performance of the system is compared with performance of existing cepstral features and previous works in this domain.http://www.doiserbia.nb.rs/img/doi/1451-4869/2022/1451-48692202239K.pdfemdhilbert spectrumhilbert huang transformcepstral featuresspeech/music classification |
| spellingShingle | Kumar Arvind Solanki Sandeep Singh Chandra Mahesh Hilbert spectrum based features for speech/music classification Serbian Journal of Electrical Engineering emd hilbert spectrum hilbert huang transform cepstral features speech/music classification |
| title | Hilbert spectrum based features for speech/music classification |
| title_full | Hilbert spectrum based features for speech/music classification |
| title_fullStr | Hilbert spectrum based features for speech/music classification |
| title_full_unstemmed | Hilbert spectrum based features for speech/music classification |
| title_short | Hilbert spectrum based features for speech/music classification |
| title_sort | hilbert spectrum based features for speech music classification |
| topic | emd hilbert spectrum hilbert huang transform cepstral features speech/music classification |
| url | http://www.doiserbia.nb.rs/img/doi/1451-4869/2022/1451-48692202239K.pdf |
| work_keys_str_mv | AT kumararvind hilbertspectrumbasedfeaturesforspeechmusicclassification AT solankisandeepsingh hilbertspectrumbasedfeaturesforspeechmusicclassification AT chandramahesh hilbertspectrumbasedfeaturesforspeechmusicclassification |