Abstract: The probability of false recognition in a continuous speech recognition system is reduced by developing a similarity measure and path information at each time point (i, j), checking whether or not the path information at the time point (i, j) is within a predetermined window restriction, and excluding a time point outside the window restriction from development of the similarity measure and path information.

Abstract: A speech analyzer for interpretation of sound includes a sound input which converts the sound into a signal representing the sound. The signal is passed through a plurality of frequency pass filters to derive a plurality of frequency formants. These formants are converted to voltage signals by frequency-to-voltage converters and then are prepared for visual display in continuous real time. Parameters from the inputted sound are also derived and displayed. The display may then be interpreted by the user. The preferred embodiment includes a microprocessor which is interfaced with a television set for displaying of the sound formants. The microprocessor software enables the sound analyzer to present a variety of display modes for interpretive and therapeutic used by the user.

Abstract: A data transfer network uses an I/O subsystem to support a main host computer in managing data transfers to and from remote data terminals. The I/O subsystem may constitute one or more units called a Line Support Processor. The Line Support Processor uses internal processor means to control a plurality of line adapters each of which has a data-comm line to a data set or data terminal. Control operations by said internal processor permit selected line adapters to operate selected types of protocols using synchronous or asynchronous transmission. Data communication information and commands in high level language data are loaded into auxiliary memories in the internal processor means and into each line adapter where the internal processor means acts to convert this language data into usable protocols.

Abstract: A method and apparatus is described for modulating a color display in which the blended color is dependent upon the magnitude of N electrical signals which vary with the parameters of an audio signal. Known color pattern generators contain too many variables for a watching subject to be able to correlate them. This invention displays a single blended color which is related to the characteristics of the sound input.

Abstract: An apparatus for detecting and storing digital data corresponding to spoken words carried by acoustic signals includes apparatus for detecting and storing the unvoiced portion of speech which often precedes the voiced portion of a word, even where the amplitude of the unvoiced portion is comparable to the background noise level. The apparatus includes dynamic storage which holds data corresponding to a fixed time period prior to detection of the larger-amplitude voiced segment. Voiced speech is detected when it exceeds a stored value related to the average background noise. At the instant of this detection, the segment of prior data held in the dynamic storage is retained for analysis as unvoiced speech.

Abstract: A monosyllabic recognition apparatus is disclosed which includes a first memory which stores reference vowel patterns respectively representing vowel categories of known reference monosyllables of a preselected language, which are classified in accordance with the type of vowel characteristics of the language, the vowel categories independently including categories corresponding to a contracted sound and a syllabic nasal sound in addition to categories of basic vowels; a second memory which stores reference consonant patterns respectively representing consonant categories of the language, which are classified in accordance with the type of consonant characteristics of the language. A characteristic extracting section generates the acoustic parameter data of the input speech, which is divided by a segment processing section into monosyllabic acoustic parameter components.

Abstract: A speech recognition apparatus includes a speech signal analyzing circuit for time-sequentially generating acoustic parameter patterns representing the phonetic features of speech signals, and phoneme reference memories each storing a plurality of reference parameter pattern vectors. A phoneme pattern vector from the speech signal analyzing circuit is compared with each of the reference pattern vectors stored in the phoneme reference memories in order to recognize an input speech. The speech signal analyzing circuit has a parameter extraction circuit for time-sequentially extracting acoustic parameter patterns representing the speech signal, a first phoneme pattern vector memory for storing a phoneme pattern vector including an acoustic parameter pattern of each frame from the parameter extraction circuit, and a second phoneme pattern vector memory for storing a phoneme pattern vector including a plurality of parameter patterns from the parameter extraction circuit.

Abstract: An apparatus and method for recognition of sentences comprised of utterances separated by short pauses, the utterances representative of both isolated words and connected words. Speech to be recognized is converted into frames of digital signals. Selected ones of the frames of digital signals are compared with isolated word and connected word templates stored in a template memory. Recognition of isolated words is done by comparing the selected frames of digital signals with the isolated word templates in accordance with a windowed dynamic programming algorithm having path boundary control, while connected word recognition is accomplished by comparing selected frames of digital signals with the connected word templates in accordance with a full DPA having path score normalization and utterance frame penalty calculation capability. Variable frame rate encoding is used to identify the selected frames of digital signals.

Abstract: An apparatus for use in transmitting compressed digital voice data includes an analyzer for compressing digitized voice data according to an algorithm which produces a root mean square of the voice data. An analog to digital converter is used to convert analog voice signals to digital data as an input to the analyzer. An AGC circuit controls to analog voice signal to keep it within predetermined limits for digitization, with the AGC setting being determined by the root mean square of the digitized data. The digitized data includes data representative of the root mean square adjusted by the inverse of the change induced by the AGC. A speech synthesizer expands the digitized data at a remote location to convert it back to analog speech signals.

Abstract: An interface between a system processor of an automated mailing system and selected peripheral devices carries peripheral support hardware and software for communication with the peripherals. The interface includes a board having a memory wherein programs for formatting communications with the peripherals are stored. A working memory for the temporary storage of commands and data for communication to the peripherals and a peripheral controller for establishing a communications link with a selected peripheral are also carried on the interface board. A replaceable PROM is carried on the interface for accessing the output enable pins of the program and working memories. The PROM is replaced in the field when a different program or working memory is to be substituted.

Abstract: In a data processing system including a central processing unit capable of operation with a plurality of operating systems, a VMSM unit is described for producing a composite decor descriptor from a plurality of possible decor descriptor formats. The VMSM unit includes an input buffer unit and an output buffer unit, a control unit to analyze an incoming DATA and provide appropriate control signals, a reconfiguration unit for reformatting the plurality of descriptor formats into a composite format, a descriptor fetch unit for retrieving a descriptor when the signals applied to the VMSM unit contain a descriptor address, and a descriptor master copy unit which contains a copy of the descriptors stored in the addressing apparatus.