A Transducer/Equipment System for Capturing Speech and Telemedicine Information for Subsequent Processing by Computer Systems
Abstract
Benchmarked speech capture data formed a corpus for the research to determine how the noise characterization information can best be used to improve speech recognition performance under tactical high noise conditions. The various speech capture improvement remedies investigated focused on a combination of methods that are matched to the FFT derived characterization of the tactical noise or medical sensor signals. These methods include stochastic canceling techniques for random (non-stationary) noise and algorithmic Feature Set subtraction for stationary noise. An important part of this investigation used tactical platform acoustic sound recordings under controlled conditions. The results of this experimentation was incorporated in speech processing algorithms for the remedy of stationary and non-stationary noise using post signal processing of Noise Feature Set Array Extraction techniques. Successful speech capture was demonstrated in noise environments up to 105 dBA using a combination of non-stationary and stationary noise post processing Noise Feature Set Extraction.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1997
- Accession Number
- ADB224296
Entities
People
- Benjamin Tirabassi