Saurabh V Raut ¹, Lavanya C Panthangi ¹, B. G. Akhil ¹, Syed Faisal Ali ², H. S. Sanjay ³, S. Bhargavi ⁴

Affiliations
1 Department of Medical Electronics, M S Ramaiah Institute of Technology, Bangalore – 560054, Karnataka, IN
2 MedNXT Innovative Technologies, IN
3 Jain University, Department of Medical Electronics, MSRIT, Bangalore – 560054, Karnataka, IN
4 Department of Telecommunication Engineering, SJC Institute of Technology, Chikkaballapura – 562101, Karnataka, IN

Abstract

Background/Objective: The objective of the present study is to classify a given speech signal by using energy as a differentiating parameter into voiced and unvoiced components due to the fact that the voiced components have a higher energy than their unvoiced counterparts. Method/Statistical Analysis: This is accomplished by dividing the speech signal into frames and by computing the short time energy of each frame. The recorded speech signal is segmented and then the energy component of these frames are obtained and then classified into voiced and unvoiced components. The current protocol involves 44 subjects, both males and females of no known vocal pathology. Predefined set of words, both in Kannada and English were recorded in a noise proof environment which was then separated into voiced and unvoiced components using MATLAB tool. Findings: The results proved a successful discrimination of the speech signal into voiced and unvoiced components based on the statistical parameters calculated for voiced as well as unvoiced components thereby providing a definite cue towards an automated approach to differentiate the speech into voiced and unvoiced components using statistical parameters. Application/Improvements: Such an approach can further be useful in various speech processing as well as speech recognition applications.

Keywords

Frame-by-frame Processing, Short Time Energy (STE), Voiced Speech, Unvoiced Speech, Windowing.

Full Text

   

H. S. Sanjay ¹, S. Bhargavi ², Syed Faisal Ali ³

Affiliations
1 Department of Electronics Engineering, Jain University, Bengaluru – 560069, Karnataka, IN
2 Department of Telecommunication Engineering, SJC Institute of Technology, P.B. No. 20, B.B. Road, Chickballapur - 562101, Karnataka, IN
3 MedNXT Innovative Technologies, 565/4, 6th Cross, HAL Second Stage, Ulsoor, Bengaluru - 560008, Karnataka, IN

Abstract

Background/Objectives: Human brain learns from conditioning. Also learning is an inherent activity exhibited by every human being. A better training/conditioning leads to a better learning and in remembering as well. Methods/Statistical Analysis: The present work focuses on the assessment of behavioural response for a predefined set of single tone sound with varying intensity after being conditioned for 20 days and after a break period of 7 days and assessing the same on day 28 for the retention based behavioural response. A pure tone complex of 1 KHz, 500 milliseconds duration was used and the test was conducted in the morning and evening in a noise free environment. A total of 44 subjects, both males and females of 20–30 years of no known auditory pathological history were considered. Findings: The results showed a distinct betterment of the auditory perception over the training period hinting at the attention abilities of the subjects. After a break of seven days, substantial information gained during the training phase was found to be retained thereby proving the retention abilities of the individuals. The presently obtained results provide a cue towards the learning abilities of human beings with gradual training and also to the extent to which the human beings can retain the aspects learnt during the training sessions. The results also demonstrated that the males have a better attention as well as retention abilities than females. Application/Improvements: The presently designed protocol is successfully able to assess the attention and retention based abilities of the individuals. This method can be extended to assess the auditory temporal resolution of professionals in case of basket ball and table tennis sports and also to assess the deterioration of the hearing perception of traffic police and the workers of fabrication and chemical industries.

Keywords

Absolute Threshold, Attention, Auditory, Behavioural Response, Conditioning, Retention, Single Tone

Full Text