Heart sound identification based on MFCC and short-term energy
| Autor: | Qingfang Meng, Yutai Wang, Boyuan Sun, Xinghai Yang |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Computer science
Speech recognition 010401 analytical chemistry Feature extraction 02 engineering and technology 021001 nanoscience & nanotechnology 01 natural sciences 0104 chemical sciences Term (time) Support vector machine Identification (information) Heart sounds Mel-frequency cepstrum 0210 nano-technology Energy (signal processing) |
| Zdroj: | 2017 Chinese Automation Congress (CAC). |
| DOI: | 10.1109/cac.2017.8244117 |
| Popis: | This paper analyzes the research status and development trend of heart sound identification at home and abroad. Concerning the dynamic characteristics and timedomain characteristics of heart sound signals, a new improved identification algorithm is proposed. It put the MFCC and shortterm energy together as new combined parameters. In order to further verify the validity of the parameters, an identification system based on support vector machine is established. In the experiment, the identification performance influenced by different parameters is compared, and the optimal parameter settings are obtained. The average recognition rate of heart sounds is over 94%. The experimental results show that the identification system with new parameters has a higher recognition rate and lower computational complexity than that with MFCC+AMFCC. The method proposed in the paper can effectively improve the speed of heart sound identification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|