Abstract: The learning method of reference pattern vectors for speech recognition in accordance with the present invention, a plurality of speech feature vectors are generated from the time series of speech feature parameter for the input speech pattern, by taking into account knowledge concerning the variation tendencies of the speech patterns, and the learning (preparation) of reference pattern vectors for speech recognition is carried out by the use of these speech feature vectors thus generated. Therefore, it becomes possible to prepare highly reliable reference pattern vectors in an easy manner from a small number of speech patterns, which makes it possible to achieve an improvement in the speech recognition factor. In particular, it becomes possible to plan an easy improvement of the reference pattern vectors by an effective use of a relatively small number of input speech patterns.

Abstract: Speaker verification is tested in a sequence of steps: speech recognition of the spoken identification code (key code) is followed by speaker verification using the sounds of the spoken identification code. If verification fails, the speaker is urged by a speech synthesizer to utter his or her name for speaker verification.

Abstract: An acoustic signal processing circuit extracts input speech pattern data and subsidiary feature data from an input speech signal. The input speech pattern data comprise frequency spectra, whereas the subsidiary feature data comprise phoneme and acoustic features. These data are then stored in a data buffer memory. The similarity measures between the input speech pattern data stored in the data buffer memory and reference speech pattern data stored in a dictionary memory are computed by a similarity computation circuit. When the largest similarity measure exceeds a first threshold value and when the difference between the largest similarity measure and the second largest measure exceeds a second threshold value, category data of the reference pattern which gives the largest similarity measure is produced by a control circuit to correspond to an input speech.

Abstract: An image display system is disclosed which includes an image filing device to pre-store data on the entire area of a large sized image; a CRT unit to partially display this large sized image on its display screen at the same scale; and an image memory to temporarily store a partial image of the large sized image, that will be displayed on this CRT as well as its surrounding image. When display area scrolling is directed by a scroll direction input device, image information which is newly required due to the given scrolling operation is read out under the control of the CPU, and the unnecessary image information is replaced or written over by the new image information, with semi-realtime, in the memory area in which the image information which became useless due to the scrolling operation had been stored in the image memory. Thus, the display image area concerning the scroll and its surrounding image area always prepared in the image memory, thereby allowing for a smooth scrolling operation.

Abstract: The apparatus comprises an illuminating system including a rotary filter for spectrum-analyzing a sample containing white blood corpuscles subjected to WRIGHT staining process, for example, and mounted on a glass slide, into monochromatic lights having different wavelengths in the visible light range, a video camera for scanning a predetermined area of the spectrum-analyzed sample for producing a picture image, a photoelectric transducer for producing an electric signal corresponding to the tone of the picture image at the sampling point in the predetermined area, a digital-analogue converter for converting the electric signal into a digital signal, a memory device for storing the output from the digital-analogue converter, a circuit for normalizing the information stored in the memory device, similarity calculating circuit for determining the similarity between the output from the normalyzing circuit and reference data, means for detecting and storing the types of the white blood corpuscles respectively corr

Abstract: The segmentation apparatus comprises means for illuminating a blood smear mounted on a slide and subjected to WRIGHT staining successively with lights having wavelengths of 410 nm and 530 nm respectively for obtaining two blood corpuscle images produced by monochromatic lights having respective wavelengths, means for producing two electric signals having levels corresponding to the tones of respective blood corpuscle images, means for converting the two electric signals into binary signals in accordance with two different threshold valves, means for obtaining the exclusive OR of the two binary signals for detecting the white blood corpuscles in the blood, and means for obtaining the logical product of said two binary signals the segmenting the red blood corpuscles in the blood.