Title :
Speech-Based Five Features Extraction and Hardware Trade-Off Design for Mental Fatigue Monitoring
Author :
Li, Zhihai ; Li, Wenshi ; Yao, Zongbao ; Li, Yaotian
Author_Institution :
Dept. of Microelectron., Soochow Univ., Suzhou, China
Abstract :
After combing the known advantages and disadvantages of the normal methods on human mental fatigue test, we measure speech signals in condition of fatigue-free and fatigue, then attract key features, and then analyze their validities. More interesting works address corresponding feature-modules designed with EDA tools. The methods are outlined as: 4~5 seconds data are sampled by PC embedded MATLAB software platform, the mean-value ratio of pre- and post-features is defined into evaluation threshold. And with the help of EDA tools named of System Generator and Xilinx ISE 11, our feature-modules design optimization are marched onto complexities´ report. The results show that five key features´ validity-sequence can list as (1) short-time energy (mean-bias 298%), (2) short-time mean amplitude (41.9%), (3) short-time cross-zero ratio (15.9%), (4) short-time self-correlation (12%), and (5) pitch (10%), just about same as their modules´ structure-sophistications. Compared with other advanced tricks on mental fatigue tests, our works may accelerate low power consumption application combined with trade-off design thinking for future study of cerebral health monitoring.
Keywords :
circuit optimisation; electronic design automation; embedded systems; feature extraction; psychometric testing; speech recognition; EDA tools; PC embedded MATLAB software platform; Xilinx ISE 11; evaluation threshold; fatigue-free speech signals; feature-modules design optimization; hardware trade-off design; human mental fatigue test; mean-value ratio; mental fatigue monitoring; pitch; short-time cross-zero ratio; short-time energy; short-time mean amplitude; short-time self-correlation; speech signals; speech-based feature extraction; system generator; Fatigue; Feature extraction; Generators; Hardware; Humans; MATLAB; Speech; MATLAB; hardware modeling; mental fatigue; optimization; speech features; speech signal;
Conference_Titel :
Information Technology, Computer Engineering and Management Sciences (ICM), 2011 International Conference on
Conference_Location :
Nanjing, Jiangsu
Print_ISBN :
978-1-4577-1419-1
DOI :
10.1109/ICM.2011.163