Downloads & Free Reading Options - Results

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.

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.

The objective of the Phase I Small Business Innovative Research (SBIR) Program Topic A93-033, entitled A Transducer/Equipment System for Capturing Speech Information for Subsequent Processing by Computer Systems is exploratory research to parameterize the speech signal, provide benchmark measurement techniques, and to assemble a superior speech capture system while minimizing the effects of noise and interference. Human verbal response under controlled conditions and when exposed to stress exhibit quantifiable differences that when assessed by computer have direct medical monitoring application. Soldiers answer queries about symptoms, well-being, or perceived capabilities while they are performing their duties. Measures of operational performance for military tasks involving communications such as requests for fire support or sending of planned target lists are collected by computer systems. Thus, demonstrating the feasibility of this transducer/equipment system as a necessary and critical first step towards the ultimate application of computer systems to collect and analyze symptoms, moods, and performance data from soldiers in real-time in training centers, the laboratory, and the field with minimal interference to ongoing soldier activities. The algorithms developed for accurate speech capture have demonstrated immunity to a broad range of acoustic and transmission media conditions which include concentrations of acoustic noise in all anticipated regions of the spectrum significant in the human voice response band. Medical monitoring, Speech recognition, Noise rejection, Speech capture, Articulation index, Human appliance device

The objective of the Phase I Small Business Innovative Research (SBIR) Program Topic A93-033, entitled A Transducer/Equipment System for Capturing Speech Information for Subsequent Processing by Computer Systems is exploratory research to parameterize the speech signal, provide benchmark measurement techniques, and to assemble a superior speech capture system while minimizing the effects of noise and interference. Human verbal response under controlled conditions and when exposed to stress exhibit quantifiable differences that when assessed by computer have direct medical monitoring application. Soldiers answer queries about symptoms, well-being, or perceived capabilities while they are performing their duties. Measures of operational performance for military tasks involving communications such as requests for fire support or sending of planned target lists are collected by computer systems. Thus, demonstrating the feasibility of this transducer/equipment system as a necessary and critical first step towards the ultimate application of computer systems to collect and analyze symptoms, moods, and performance data from soldiers in real-time in training centers, the laboratory, and the field with minimal interference to ongoing soldier activities. The algorithms developed for accurate speech capture have demonstrated immunity to a broad range of acoustic and transmission media conditions which include concentrations of acoustic noise in all anticipated regions of the spectrum significant in the human voice response band. Medical monitoring, Speech recognition, Noise rejection, Speech capture, Articulation index, Human appliance device

This report describes results of an examination of four methods for processing speech so as to enhance its intelligibility in the presence of wideband random noise at the source. The four methods were: (1) INTEL, a method which involves processing in both the first and second order spectral domains; (2) Spectral subtraction, which involves a simple subtraction of the average noise spectrum from the first-order spectrum; (3) Minimum mean square error filtering, which involves filtering speech in such a way as to minimize the mean square error between a signal and its expected value in noise; and (4) Methods based upon suppressing the frequency content of a speech plus noise signal between pitch harmonics of the speech signal. To carry out a study of methods of enhance speech intelligibility in noise, two general-purpose computer processing systems were implemented. The first, a terminal interactive system for generation, analysis, and graphic display of synthetic voiced speech sounds, provided considerable insight into the effect of various processing algorithms upon speech and upon speech in noise. The second computer processing system has been developed for the processing of real speech. It involves use of a DDP-116 data converter and a Honeywell 6000 Computer.