Suman Senapati

Learn More
Pre-processing of Speech Signal serves various purposes in any speech processing application. Out of these, silence/unvoiced portion removal along with endpoint detection is the fundamental step for applications like Speech and Speaker Recognition. The proposed method uses Probability Density Function (PDF) of the background noise and a Linear Pattern(More)
In this article a method of computing similarity of two Chinese pop songs is presented. It is based on five attributes extracted from the audio signal. They include music instrument, singing voice style, singer gender, tempo, and degree of noisiness. We compare the computed similarity measures with similarity scores obtained with subjective listening by(More)
— Speaker recognition system needs an efficient feature extraction process and an appropriate speaker model developed from these features. The key issue in robust Automatic Speaker Recognition (ASR) system is to yield good recognition accuracy regardless of the mismatch in the environmental conditions between training and testing time. The work uses(More)
Effective treatment of tannery wastewater prior to discharge to the environment as per environmental regulations remains a big challenge despite efforts to bring down the concentrations of the pollutants which are often quite high as measured in terms of chemical oxygen demand (7800 mg/L), total dissolved solids (5400 mg/L), chloride (4260 mg/L), sulphides(More)
— Automatic Speaker recognition (ASR) is a pattern recognition problem that involves the process of automatically recognizing the speaker from their voices. Password protected speaker recognition system gives an extra security to the system where a person is not only identified by his natural voice bio-metric but also needs to remember a password (e.g. a(More)
  • 1