Abstract: A voice recording and reproducing apparatus which includes a voice encoder for encoding a voice signal into a voice code, an address counter, a voice code memory in which the voice code is circulatively stored as specified by the address counter, a discriminator for determining whether the voice signal inputted is a voiced signal or whether the voice signal inputted is a silent signal, and a register for storing an address value of the address counter when the discriminator indicates that the silent signal has changed into the voiced signal. During reproduction, the starting address of the reproduction is determined by a stored address. The stored address represents the address value in the address counter at the time when the discriminator indicates that a silent signal has changed to a voiced signal.

Abstract: A Universal Memory Loader Verifier (UMLV) is disclosed. The loader comprises a system used to load and verify Operational Flight Programs (OFP) into an unlimited number of different types of avionics computers without the need for adding additional hardware (with the exception of an additional cable that may be unique to each particular computer being loaded and verified). The disclosed Universal Memory Loader Verifier (UMLV) consists of a portable, off the shelf, militarized, arm held, battery backed Personal Computer. The PC contains a custom interface card for different types of applications. The PC output is connected to a buffer box having a custom card therein by means of a cable. The buffer box is connected to a single ended driver/receiver type avionics computer through a unique cable. This connection requires an additional cable for each computer type. For all other applications, the PC is connected directly to the avionics computer by means of a unique cable.

Abstract: An apparatus and method for verifying the identity of an unknown user of a telephone calling card service is disclosed which receives identification information corresponding to a valid user of the service, requests the unknown user to speak an authorization phrase without disclosing the authorization phrase to the unknown user, receives the unknown user's speech signal in response to the request, and verifies the identity of the unknown user based on the received speech signal. Other apparatus, systems, and methods are also disclosed.

Abstract: A subband coding method and encoding/decoding system suitable for a high definition television which is possible to compress data more effectively. Frequency band of input data is analyzed into a high-band component and a low-band component in the two-dimensional diagonal direction, the diagonal low-band component is analyzed again into orthogonal high-band component and low-band component and the diagonal high-band component and the orthogonal high-band component are coded, and then the orthogonal low-band component is continuously analyzed until it has a desired size by repeating the previous analysis procedures.

Abstract: The invention relates to a method of coding a sampled speech signal vector by selecting an optimal excitation vector in an adaptive code book. This optimal excitation vector is obtained by maximizing the energy normalized square of the cross correlation between the convolution of the excitation vectors with the impulse response of a linear filter and the speech signal vector. Before the convolution the vectors of the code book are block normalized with respect to the vector component largest in magnitude. In a similar way the speech signal vector is block normalized with respect to its component largest in magnitude. Calculated values for the squared cross correlation C.sub.I and the energy E.sub.I and stored corresponding values C.sub.M, E.sub.M for the best excitation vector so far are divided into a mantissa and a scaling factor with a limited number of scaling levels. The number of levels can be different for squared cross correlation and energy. During the calculation of the products C.sub.I .multidot.E.

Abstract: This invention relates to a control system for controlling equipment provided inside a vehicle utilizing a speech recognition apparatus inside the vehicle. This control system includes an in-phase component detector (4) for detecting an in-phase component of voice signals from microphones (1), a phase shift and in-phase component detector (5) for shifting a phase of the voice signals to detect an in-phase component, and a command seat discriminator (6) for comparing output levels of the in-phase component detector (4) and the phase shift and in-phase component detector (5).

Abstract: A speech coder includes an LPC analyzer, a difference signal generating section, a first code book, a second code book, and a multiplexer. The LPC analyzer divides an input discrete speech signal into signal components in units of frames each having a predetermined time length, and obtains a spectrum parameter representing a spectrum envelope of the speech signal. The difference signal generating section obtains a difference signal by dividing the frame into subframes each having a predetermined time length, and predicting a pitch parameter representing a long-term correlation on the basis of a past sound source signal The first code book stores a signal formed beforehand by off line training learning based on the difference signal. The second code book stores a signal having predetermined characteristics or a signal formed beforehand by learning.

Abstract: A pitch extraction apparatus for extracting (detecting)a pitch of an acoustic signal which includes circuitry for calculating the stability of the acoustic signal. The stability calculation exhibits a larger value as the amplitude of the acoustic signal is larger and when the frequency is low. Pitch extraction is performed using the calculated stability. In addition, a pitch extraction apparatus which includes a pitch extractor for extracting a pitch of an acoustic signal by discriminating whether or not an input is a voiced or voiceless sound. Based on the determination that the input is a voiceless sound, the input to or the output from the pitch extractor will be inhibited.

Abstract: A method for encoding syllables of a language, particularly the Japanese language, and for facilitating the extraction of sound codes from the input syllables, for voice recognition or voice synthesis includes the step of providing a syllable classifying table, in which each syllable is represented by an upper byte code indicating the consonant part of the syllable and a lower byte code indicating the non-consonant part of the syllable. The consonants constitute a first category of data classified by phonetic features, while the non-consonants constitute a second category of data classified by phonetic features, so that the extraction of consonant or non-consonant sounds can be made by a search in only the first or the second categories.

Abstract: A noise-contained voice signal is cepstrum-analyzed to determine a peak and a mean-value thereof. When a peak is present, the signal is determined to be a vowel portion, and when a mean-value is large, the signal is determined to be a consonant portion, thereby allowing a voice portion to be accurately determined. Further, utilizing the detected result, noise is accurately canceled.

Abstract: In a computer network system in which a plurality of computer systems managed by different managers are connected, each computer system in the network system is provided with a group of tables for storing the characteristics of computer systems in the network system with which the site of that computer system is communicatable, the cumulative total of account information when that computer system requested the execution of jobs to another site, the cumulative total of account information when the site of that computer system executed jobs requested from another site, and the calculated value of the balance of accounts between the site of that computer system and each site in correspondence to each of sites in the network system and is also provided with a group of processing programs.

Abstract: To improve the accuracy of phoneme discrimination, a first phoneme discrimination method composes analyzing, not only static information on a voice but also dynamic information on the voice, power variations of the voice as a power-change pattern (PCP) and spectrum parameter variations of the voice as a time spectrum parameter pattern (TSP). After rough clustering based on the PCP, detailed classification is conducted using the TSP so that the voice is hierarchically discriminated to obtain phoneme symbols. This invention also provides a second phoneme discrimination method. To improve the accuracy of phoneme discrimination by a recognition system for unspecified, independent speakers, plural spectrum parameter codebooks classified in advance depending on voice qualities are provided.

Abstract: A technique for wordspotting based on hidden Markov models (HMM's). The technique allows a speaker to specify keywords dynamically and to train the associated HMM's via a single repetition of a keyword. Non-keyword speech is modeled using an HMM trained from a prerecorded sample of continuous speech. The wordspotter is intended for interactive applications, such as the editing of voice mail or mixed-media documents, and for keyword indexing in single-speaker audio or video recordings.

Abstract: A CELP type speech coding system is provided with an arithmetic processing unit which transforms a perceptual weighted input speech signal vector AX to a vector .sup.t AAX, a sparse adaptive codebook which stores a plurality of pitch prediction residual vectors P sparsed by a sparse unit, and a multiplying unit which multiplies the successively read out vectors P and the output .sup.t AAX from the arithmetic processing unit. In addition, the CELP type speech coding system includes a filter operation unit which performs a filter operation on the vectors P, and an evaluation unit which finds the optimum vector P based on the output from the filter operation unit, so as to enable reduction of the amount of arithmetic operations.

Abstract: For facilitating the transmission or recording of digital audio signals in a narrow band channel or at a reduced data rate without deterioration of audio quality detectable by the human ear, a digital audio signal is subdivided into overlapping time window segments and the segments are subjected to fast Fourier transformation, with generation of scaling factors. The spectral values resulting from the transformation are converted into separate magnitude and phase values, the former being logarithmically quantized and the latter being linearly quantized. The magnitude values corresponding to an upper portion of the spectrum are collected into groups of a size that increases towards the high frequency end of the spectrum and the magnitude values of each group are rms averaged, so that one value can serve in place of several magnitude values, thereby reducing the data to be transmitted or recorded.

Abstract: A cepstrum calculating device obtains a cepstrum of a voice signal and a mean-value calculation device cepstrum means output. A threshold setting device sets a voice detection threshold level on the basis of the cepstrum mean-value output. A cepstrum addition section adds a cepstrum value exceeding the cepstrum mean-value. A comparator compares the cepstrum output from the cepstrum addition section with the threshold output signal from the threshold setting device, thereby to output a voice-detection signal.

Abstract: In many applications involving the coding and processing of speech signals the relevant applicable codebook is one which may be termed a sparse codebook. That is, the majority of elements in the codebook are zero valued. The searching of such a sparse codebook is accelerated in accord with the present invention by generating auxiliary information defining the sparse nature of the codebok and using this information to assist and speed up searches of the codebook.In a particular method of searching the calculation of the distance between a target vector and a stored codebook vector is enhanced by use of a distortion metric derived from energy terms and correlation terms of the codebook entries. Calculation of these energy and correlation terms is speeded up by exploiting the sparseness of the codebook entries. The non-zero elements (NZE) of the space codebook are each identified and are defined by their offset from a reference point.

Abstract: A voice interactive computer system having voice digitizing circuitry for digitizing voice input from an operator. The voice digitizing circuitry is preferably placed on a computer card in operative association with a central processing unit in the computer. The digitized voice input may be selectively replayed and compared with a prerecorded language vocabulary stored on a compact disc read only memory connected to the computer. The compact disc read only memory is also used for storing software which provides interaction between the voice digitizing circuitry and the computer central processing unit and random access memory in the computer. The voice digitizing circuitry may be placed on a separate computer card positioned in a slot in a bus in operative association with the central processing unit or combined with other cards. The digitized voice input may also be stored on magnetic media such as a computer disc for later review by others, such as a teacher.

Abstract: A voice processing apparatus capable of varying the speed of speech, in which a voice of a predetermined duration is represented by feature parameters and propriety information indicating whether a change in the speech speed is permitted or not. During voice synthesis, the speech speed is varied by skipping or repeating only the feature parameters for which the variation in speech speed is permitted by the associated propriety information.

Abstract: A new way of determining correlation coefficients for stochastic codebook vectors for CELP coding of speech takes advantage of the sparsely populated nature of stochastic codebook vectors. N valued input signals (e.g., convolution vectors) to be correlated with N valued codebook vectors are fed to an N by N multiplexer or other selection means and the signal values either passed to an accumulator or not according to the state of N select inputs or other identification means determined from a memory store (e.g., an EPROM) whose entries correspond to the non-zero values of the codebook vectors. The accumulator output is the correlation of the codebook vector with the input signal. A sequencer steps through the entire codebook to provide correlation values for each vectors. The results are used to determine the optimum stochastic codebook vector for replicating the particular speech frame being analyzed.