Abstract: An operation device having the element number and delay time of the operation circuitry reduced is realized by a purely logical approach. An operation method based on encoding is concretely and efficiently logic-designed to provide an encoding operation device operators of an operation system are extended if required to treat as logic functions with the base number r. When r=2, using a generating function as a new representation of a mapping, a new operation system is logic-designed under encoding conditions and logic expression simplifying conditions, or the new operation system is logic-designed by matching the topologies of input/output relation of the operators of the original operation system and the new operation system. The operation device satisfying the encoding conditions and logic expression simplifying conditions achieves speeding up and low power consumption.

Abstract: A book database stores at least phonetic signal information including phoneme information and rhythm information as document data, a central system transmits phonetic signal information stored on the book database to a terminal and the terminal receives the phonetic signal information is then carried out at the terminal and the document is then recited via synthesized sounds.

Abstract: An apparatus and a method for processing a natural language arranged so as to improve the speech recognition rate. In an example search section, the degree of similarity between each of a plurality of examples of the actual use of the language stored in an example data base and each of a plurality of probable recognition results output from a recognition section, and one of the examples corresponding to the highest degree of similarity is selected. A final speech recognition result is obtained by using the selected example. The example search section calculates the degree of similarity by weighting the degree of similarity on the basis of a context according to at least one of the examples previously selected.

Abstract: A translation apparatus and a translation method arranged to facilitate the operation of inputting a speech and to obtain a correct translation. When a speech in Japanese is input to a microphone by a user, it is recognized in a speech recognition section and one or more words constituting the speech are output to a system control section. The system control section searches Japanese sentences stored in a first language sentence storage section to find one of them most similar to a combination of one or more words output from the speech recognition section. The Japanese sentence thereby found is output through an output section. If this Japanese sentence is correct, the user operates one of control keys. The system control section then searches English sentences stored in a second language sentence storage section to find one of them corresponding to a translation of the Japanese sentence output as a search result, and outputs the English sentence thereby found through the output section.

Abstract: A book database stores at least phonetic signal information including phoneme information and rhythm information as document data, a central system transmits phonetic signal information stored on the book database to a terminal and the terminal receives the phonetic signal information is then carried out at the terminal and the document is then recited via synthesized sounds.

Abstract: In a speech recognizing apparatus, a grammatical qualification of a proposed speech recognition result candidate is judged without using a grammatical rule. The speech recognizing apparatus for performing sentence/speech recognition is comprised of an analyzing unit for acoustically analyzing speech inputted therein to extract a feature parameter of the inputted speech; a recognizing unit for recognizing the inputted speech based upon the feature parameter outputted from said analyzing unit to thereby a plurality of proposed recognition result candidates; an example data base for storing therein a plurality of examples; and an example retrieving unit for calculating a resemblance degree between each of said plurality of proposed recognition result candidates and each of the plural examples stored in the example data base and for obtaining the speech recognition result based on said calculated resemblance degree.

Abstract: A mapping determination method for obtaining mapping F from an N-dimensional metric vector space .OMEGA..sub.N to an M-dimensional metric vector space .OMEGA..sub.M has the following steps to get the optimal mapping quickly and positively. In the first step, complete, periodic, L.sub.m basic functions g.sub.m (X) according to the distribution of samples classified into Q categories on the N-dimensional metric vector space .OMEGA..sub.N are set. In the second step, a function f.sub.m (X) indicating the m-th component of the mapping F is expressed with the linear sum of the functions g.sub.m (X) and L.sub.m coefficients c.sub.m. The third step provides Q teacher vectors T.sub.q =(t.sub.q.1, t.sub.q.2, t.sub.q.3, . . . , t.sub.q.M) (where q=1, 2, . . . , Q) for the categories on the M-dimensional metric vector space .OMEGA..sub.M, calculates the specified estimation function J, and obtains the coefficients c.sub.m which minimize the estimation function J. In the fourth step, the coefficients c.sub.

Abstract: A voice recognition device according to the present invention including a voice analyzer for acoustically analyzing voice every predetermined frame unit to extract a feature vector X, a converter for subjecting the feature vector X output from the analyzer to a predetermined conversion process, and a voice recognizer for recognizing the voice on the basis of a new feature vector output from the converter, wherein the converter conducts the predetermined conversion processing according to a mapping F from an N-dimensional vector space .OMEGA..sub.N to an M-dimensional vector space .OMEGA..sub.M, the feature vector X is a vector on the N-dimensional vector space .OMEGA..sub.N and the function f.sub.m (X) of an m-th component of the mapping F is represented by the following linear summation of the products of functions g.sub.m.sup.k (X) and coefficients c.sub.m.sup.k of L.sub.m : ##EQU1## Each function g.sub.m.sup.k (X) may be set to a monomial.

Abstract: A map determination method and apparatus for calculating the coefficients to give a minimum evaluation function quickly and reliably where a map is expressed as the linear sum of a function g.sub.i (X) and a coefficient c.sub.i while a map for transforming a N-dimensional vector (x.sub.0, x.sub.1, x.sub.2, x.sub.3) to a M-dimensional vector y is being decided. The coefficient ci for the map is obtained by giving a learning sample and a teaching sample, obtaining an evaluation function and solving a simultaneous linear equation for which the partial differential is zero.

Abstract: A pattern matching multiplies distances between an input pattern and standard patterns by distance-scale correcting weight coefficients respectively prepared for the standard patterns. This yields a distance corresponding to a category shape of a standard pattern and enhance an input pattern recognition ratio. A pattern recognition apparatus stores distance-scale correcting weight coefficients respectively prepared for all standard patterns in storage means. Distances between stored standard patterns and an input pattern generated by input pattern generating means are calculated. The calculated distance is multiplied by a weight coefficient stored in the storage means in accordance with the standard pattern used for calculating the distance from the input pattern. This structure reduces the number of templates when providing the standard patterns as multiple templates and, at the same time, enhances the input pattern recognition ratio.

Abstract: A noise signal supplied from a microphone by way of an analog to digital converter is Fourier converted to calculate a power spectrum of the noise signal by a Fourier converting section. A system controller compares an average value of the power spectrum of the signal being outputted from the microphone at present and an average value of the power spectrum of a noise signal stored in a noise memory at present with each other. When the system controller determines that the difference between the average value of the power spectrum of the signal being outputted from the microphone at present and the average value of the power spectrum of the noise signal stored in the noise memory at present is higher than a predetermined reference value, it outputs a controlling signal to a sound storing and reading out section to store the signal being outputted from the microphone at present into the noise memory.

Abstract: A speech recognition system includes an acoustic analyzer which produces a time sequence of acoustic parameters from an input speech signal in an utterance boundary thereof, and estimates a trajectory in a parameter space from the time sequence of acoustic parameters. The trajectory is re-sampled in the parameter space at predetermined constant intervals sequentially each time the acoustic parameters are produced by the acoustic analyzing means, thereby producing an input utterance pattern. The input utterance pattern is matched with reference speech patterns to recognize the input speech signal. The speech recognition system also has an utterance boundary detector for detecting the utterance boundary of the input speech signal. The trajectory is re-sampled while the utterance boundary is being detected by the utterance boundary detector.

Abstract: A code conversion table, in which a code of a voice with noise added thereto and a code of a voice without noise are associated with each other in terms of probability, is referred to in a code converter. Using the code converter, a code is obtained in a vector quantizer by vector-quantizing cepstrum coefficients extracted from the voice with noise added thereto, and is converted into a code of a voice obtained by suppressing the noise in the voice with noise added thereto. Linear predictive coefficients are obtained from the code, and the voice signal is reproduced in a synthesis filter according to the linear predictive coefficients.

Abstract: A speech recognition method and apparatus in which a plurality of time-sequential acoustic parameters are derived from a segmented input speech signal and are used to form a first trajectory that is time normalized. The time-normalized trajectory is sampled at predetermined lengths therealong and the sampling results used to form a new time-normalized trajectory with equally spaced points ("dots" on the graph), which is compared with a plurality of previously registered trajectories until a match is found between the new time-normalized trajectory and one of the registered trajectories, at which time an indication of the results of the matching is produced. A silence acoustic parameter can also be added to the time-sequential acoustic parameters so that the time-normalized trajectory can start and end from a point of silence.

Abstract: Control reference pattern candidates corresponding to a verification reference patterns of a registered speaker are synthesized by connecting unit speech patterns of a plurality of speakers. A plurality of control reference patterns similar to the verification reference pattern are determined from among the control reference pattern candidates. First dissimilarity between an input pattern of a speaker to be verified and the verification reference pattern specified by the registered speaker and second dissimilarity between the input pattern and the control reference patterns specified by the registered speaker are calculated. The speaker to be verified is judged as the registered speaker on the basis of the first and second dissimilarities.

Abstract: Pattern matching, for speech recognition, wherein distances are determined between the input pattern and many reference patterns. However the distances are determined with the reference pattern at a time slant to the input pattern and the determination is repeated for different starting values of the input patterns. Dynamic programming (DP) matching is conducted based on these distances. Boundary conditions may be determined for different starting values independent of other starting values because allowed paths do not reverse directions on the scale of the gradations.

Abstract: A pattern matching system and method in which feature vectors of an input pattern to be identified are compared with a plurality of stored reference patterns in order to identify the input pattern. A number L of feature vectors from the input pattern and a feature vector from one of the reference patterns are read into a distance computation unit, under control of a pattern matching control unit. Inter-vector distances are calculated and passed to an asymptotic equation computation unit, which calculates an overall dissimilarity vector for each reference pattern. Because L feature vectors from the input pattern are read into the distance computation unit at a time, memory and reference pattern feature vector transfer requirements are decreased.

Abstract: Apparatus for obtaining an orthogonal transformer for use in signal analysis. This apparatus is especially useful in cepstral analysis where vocal tract characteristics of a signal are separated from a sound source. A buffer memory 10 temporarily stores input time series data and an orthogonal transformation is carried out by an orthogonal transform means 20 by multiplying each predetermined data read sequentially out of the buffer memory 10 by a predetermined twiddle factor. A controller 30 is used to specify the data read out of the buffer memory 10 and for giving the twiddle factor a value of 1 and r/2.sup.l corresponding to the magnitude of the real and imaginary part of the twiddle factor. Cepstrum information is obtainable using simple hardware to analyze the data generated by the orthogonal transformer.

Abstract: In a speech signal processing system for transmission or recognition, cepstrum data is normalized by subtraction from its straight-line approximation. As a result, personal and transmission characteristics are eliminated, and both data and subtraction computations are reduced.

Abstract: A voice responsive telephone adapter, or speech recognition adapter, for use with a telephone set having for example, telephone answering capabilities. The voice responsive telephone adapter may be used to dial telephone numbers or control auxiliary functional capabilities relating the message playback, for example in response to recognized verbal commands, such as, for example, names or operational functions.