Abstract: A method and apparatus that provide for automatic speech transcription that may be used transcribe structured reports. The method and apparatus provide for speaker dependent, continuous speech recognition using a limited vocabulary. Transcription is based on recognition of a vocabulary of sounds followed by a translation to text. The translation to text matches spoken sounds to sounds contained in similar recorded text sequences. Training involves speaking a set of words with the desired sounds imbedded therein. The method and apparatus recognize phrases, not words, and works well in a radiology or similar application because of the use of a very limited vocabulary to generate reports.

Abstract: Apparatus and methods for compressing an audio signal. An analog to digital converter is used to digitize the audio signal. A linear predictor processes the digitized audio signal to attenuate coherent noise and produce a residual output signal that is representative of the audio signal. An improved synchronized overlap add processor employs a one bit correlator and a smoothly-shaped window compresses the digitized audio signal. The synchronized-overlap-add processing may be used with voice or audio processing systems to change the time scale of the voice (audio) signal without changing the pitch of the processed signal. The synchronized-overlap-add processing may also be used to reduce noise in the processed signal. The present synchronized-overlap-add processing technique makes the computations required very quick, improving the utility of the processing.

Abstract: A compressing a voice signal by the steps of (a) digitizing an input signal that includes a voice signal, the input signal including a coherent noise component; and (b) compressing the digitized voice signal with a synchronized overlap add processor (20). So as to prevent the synchronized overlap add processor from locking to the coherent noise component, the step of compressing includes an initial step of applying the digitized input signal to a linear predictor (16), the linear predictor having time constants selected for attenuating the coherent noise component of the input signal. The residual signal output of the linear predictor includes the voice signal, and an uncorrelated noise component if one is present in the input signal. The operation of the synchronized overlap add processor also functions to attenuate the incoherent noise component.

Abstract: A signal detector discriminates between signals manifesting noise and signals manifesting information, both of which appear at an input. A analog-to-digital converter circuit samples the signals and a Fourier filter determines, for each signal sample, energy content of each of a plurality of frequency cells in the sample. A processor then determines the mean energy content and the average variance of energy content in all frequency cells in the signal sample. The mean energy content and average variance of energy content of the signal sample are then compared, and if the comparison indicates an approximate equality, the sample is declared to be noise. The processor further determines a centroid center frequency for the frequency cells in the sample which indicates, if it is on-center, that the sample is likely to be noise. The processor further determines the bandwidth of the Fourier components of the input signal, to determine if it is indicative of noise.