Speech feature extraction using linear Chirplet transform and its applications*
ABSTRACTMost speech processing models begin with feature extraction and then pass the feature vector to the primary processing model. The solution's performance mainly depends on the quality of the feature representation and the model architecture. Much research focuses on designing robust deep...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-07-01
|
| Series: | Journal of Information and Telecommunication |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/24751839.2023.2207267 |
| _version_ | 1797771240520286208 |
|---|---|
| author | Hao Duc Do Duc Thanh Chau Son Thai Tran |
| author_facet | Hao Duc Do Duc Thanh Chau Son Thai Tran |
| author_sort | Hao Duc Do |
| collection | DOAJ |
| description | ABSTRACTMost speech processing models begin with feature extraction and then pass the feature vector to the primary processing model. The solution's performance mainly depends on the quality of the feature representation and the model architecture. Much research focuses on designing robust deep network architecture and ignoring feature representation's important role during the deep neural network era. This work aims to exploit a new approach to design a speech signal representation in the time-frequency domain via Linear Chirplet Transform (LCT). The proposed method provides a feature vector sensitive to the frequency change inside human speech with a solid mathematical foundation. This is a potential direction for many applications. The experimental results show the improvement of the feature based on LCT compared to MFCC or Fourier Transform. In both speaker gender recognition, dialect recognition, and speech recognition, LCT significantly improved compared with MFCC and other features. This result also implies that the feature based on LCT is independent of language, so it can be used in various applications. |
| first_indexed | 2024-03-12T21:34:40Z |
| format | Article |
| id | doaj.art-993f6de1fc2046089139142a26c22c57 |
| institution | Directory Open Access Journal |
| issn | 2475-1839 2475-1847 |
| language | English |
| last_indexed | 2024-03-12T21:34:40Z |
| publishDate | 2023-07-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Journal of Information and Telecommunication |
| spelling | doaj.art-993f6de1fc2046089139142a26c22c572023-07-27T11:47:07ZengTaylor & Francis GroupJournal of Information and Telecommunication2475-18392475-18472023-07-017337639110.1080/24751839.2023.2207267Speech feature extraction using linear Chirplet transform and its applications*Hao Duc Do0Duc Thanh Chau1Son Thai Tran2Vietnam National University, Ho Chi Minh City, VietnamVietnam National University, Ho Chi Minh City, VietnamVietnam National University, Ho Chi Minh City, VietnamABSTRACTMost speech processing models begin with feature extraction and then pass the feature vector to the primary processing model. The solution's performance mainly depends on the quality of the feature representation and the model architecture. Much research focuses on designing robust deep network architecture and ignoring feature representation's important role during the deep neural network era. This work aims to exploit a new approach to design a speech signal representation in the time-frequency domain via Linear Chirplet Transform (LCT). The proposed method provides a feature vector sensitive to the frequency change inside human speech with a solid mathematical foundation. This is a potential direction for many applications. The experimental results show the improvement of the feature based on LCT compared to MFCC or Fourier Transform. In both speaker gender recognition, dialect recognition, and speech recognition, LCT significantly improved compared with MFCC and other features. This result also implies that the feature based on LCT is independent of language, so it can be used in various applications.https://www.tandfonline.com/doi/10.1080/24751839.2023.2207267speech representationtime-frequency domainlinear chirplet transforminstantaneous frequencyspeech processing |
| spellingShingle | Hao Duc Do Duc Thanh Chau Son Thai Tran Speech feature extraction using linear Chirplet transform and its applications* Journal of Information and Telecommunication speech representation time-frequency domain linear chirplet transform instantaneous frequency speech processing |
| title | Speech feature extraction using linear Chirplet transform and its applications* |
| title_full | Speech feature extraction using linear Chirplet transform and its applications* |
| title_fullStr | Speech feature extraction using linear Chirplet transform and its applications* |
| title_full_unstemmed | Speech feature extraction using linear Chirplet transform and its applications* |
| title_short | Speech feature extraction using linear Chirplet transform and its applications* |
| title_sort | speech feature extraction using linear chirplet transform and its applications |
| topic | speech representation time-frequency domain linear chirplet transform instantaneous frequency speech processing |
| url | https://www.tandfonline.com/doi/10.1080/24751839.2023.2207267 |
| work_keys_str_mv | AT haoducdo speechfeatureextractionusinglinearchirplettransformanditsapplications AT ducthanhchau speechfeatureextractionusinglinearchirplettransformanditsapplications AT sonthaitran speechfeatureextractionusinglinearchirplettransformanditsapplications |