Nec Corporation

Hitachi, Ltd.

Nippon Electric Co., Ltd.

Masao Watari

Akira Ohsawa

Hideki Nishino

Toru Onodera

Seibi Chiba

Takao Watanabe

Hiroshi Shimizu

Hiroaki Sakoe

Kazunaga Yoshida

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.

Speaker verification system

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.

Pattern matching method using restricted matching paths and apparatus

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.

Pattern matching system using dynamic programming

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.

Orthogonal transformer and apparatus operational thereby

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.

Pattern feature extracting system

A start point vicinity of an uttered input speech pattern is set. DP-matching is performed between the input speech pattern and a plurality of reference patterns obtained by connecting previously prepared reference patterns in the start point vicinity of a portion for the head word of the input speech pattern. A point within the start point vicinity is determined as a temporary start point. The dissimilarity proportional to the time length of the reference pattern is calculated and then converted into a value proportional to the time length of the input pattern from the temporary start point. The dissimilarity measure between the input speech pattern and the reference pattern on the second and the following digits are determined as a value proportional to the time length of the input speech pattern. The end time point of the input speech pattern is determined on the basis of the minimum value of a normalized dissimilarity measure and by the time length of the input speech pattern.

Continuous speech recognition apparatus

On pattern matching an input pattern arranged along a first time axis to each concatenation of patterns selected from reference patterns and arranged along a second time axis with feature vectors of the input pattern and the concatenation placed at a common frame period, a dynamic programming algorithm is used by classifying the reference patterns into classes in compliance with reference pattern lengths and by giving variable block widths to slant parallelogrammic blocks of a common block slope. The variable widths should be decided for the respective classes. Preferably, a k-th class comprises a reference pattern of a reference pattern length which is not shorter than .beta.kW and is shorter then .beta.(k+1)W, where .beta. represents the block slope and W, a fundamental block width determined by the block slope under a minimum of the reference pattern lengths. In this event, the variable block width is equal to kW. The algorithm is carried out by scaling the first time axis, not by the frame period, but by block numbers assigned to slant parallelogrammic blocks having the fundamental width in common and by checking whether or not each block number is an integral multiple of k.

Pattern recognizing device with pattern matching in slant

A recognition system for recognizing a plurality of continuous hand-written characters, employing a first memory in which isolated characters are stored, and a second memory which stores information, including interstroke character information, for connecting isolated characters. According to various embodiments of the invention, this interstroke information may be stored as part of a continuous character, or by itself.

Continuous characters recognition system

An input system for a voice recognizer circuit wherein a cue signal is issued to the user to indicate system readiness. A voice detector detects the presence of a voice signal. Control circuitry detects if a voice signal is detected prior to the end of the initial cue signal and, if so, causes a second cue signal to be issued, thereby preventing a loss of voice input. The voice detector can also be used to selectively switch an active one of a plurality of user channels to one of a smaller number of voice recognizers.

Voice input system

A pattern recognition apparatus for recognizing spoken words of a nonspecific speaker or of a specific speaker. A reference pattern composed of a sequence of feature vectors, each composed of n feature parameters, b.sub.i, is stored. The reference pattern represents a form of average of said words to be recognized as determined by multiple reference speakers speaking the same words or by the specified speaker speaking said words several times. A deviation pattern composed of a sequence of feature vectors composed of n feature parameters, w.sub.i /2, is stored. The deviation pattern is a measure of the deviation from the reference of the repeated utterances of the reference speakers or the specified speaker. An input pattern, representing the utterances of a speaker, is composed of a sequence of feature vectors, each composed of n feature parameters, a.sub.i, and is stored. A measure of the similarity of the input and reference patterns is calculated, taking into account the deviation pattern, according to one of several possible distance formulae. Basically, a distance parameter calculated for each corresponding input, reference and deviation parameter is set to zero value if the input parameter is inside the deviation range of the reference parameter, and is otherwise calculated to be a finite value.

Pattern distance calculating equipment

A continuous speech recognition system determines the similarity between input patterns and reference patterns over time such that similarities between previously spoken speech patterns and reference patterns are determined while speech continues to be spoken. Degrees of dissimilarity at arbitrary reference pattern word times are determined asymptotically and are recorded. The minimum degree of dissimilarity is determined and the corresponding word is categorized. Recognition decisions are ultimately made in reverse chronological order.

Continuous speech recognition system

A multiple channel voice I/O system including a control device and switching mechanism for enabling the system to handle a greater number of user channels than there are recognition inputs. The control unit responds to two types of commands from a host system, the first type indicating a voice output operation and the second type indicating a voice input/recognition operation. During voice output for any user channel, that channel is not connected to any input terminal of the recognition unit. During voice input/recognition operation, the control unit searches for an unoccupied input terminal and connects it to a user channel.

Multiple-channel voice input/output system

A miniature computer has a main section which includes a central processor, a read only memory storing a monitor program, a random access memory for executing the monitor program and a controlling circuit for peripheral equipment, and a hand-held controller electrically connected to the main section through a flat cable, the hand-held controller having a keyboard and display device such that the keyboard has keys of numerals 0 to 9 and the alpha characters A to Z for enabling data in the form of symbolic language to be input according to an assembler program. The assembler program is stored in the read only memory and the symbolic language data is converted to corresponding machine language. The hand-held controller includes a key input system which utilizes encoders rather than mulitplexers to detect and transmit key input data data to the main section.

Miniature computer with separate hand-held controller

A reproducing circuit is provided for reproducing digital information recorded in a cassette tape by frequency modulation in which different first and second digital logic levels are respectively represented by first and second repeated signals having respective first and second repeated frequencies, the first repeated frequency being higher than the second. A pulse forming circuit produces first and second pulse signals having the first and second repeated frequencies in response to the signals recorded on the cassette tape. The first or second pulse signals are applied to a one-shot circuit as a trigger signal and to the control input terminal of a flip-flop circuit as a control signal. The output of the one-shot circuit is supplied to the data input terminal of the flip-flop circuit, whereby reproduced digital information corresponding to the digital information recorded on the cassette tape is derived from the output terminal of the flip-flop circuit.

Miniature computer

A minature computer comprising a main section which includes a central processor, a read only memory storing a monitor program, a random access memory for executing the monitor program and a controlling circuit for peripheral equipments developed which has a hand-held controller electrically connected to the main section through a flat cable, having a keyboard and display device such that the keyboard has keys of a numeral 0 to 9 and the alpha characters A to Z for enabling symbolic languages to be input according to an assembler program. The assembler program is stored in the read only memory and the symbolic languages are converted to corresponding machine languages. The main section has a first jack capable of inputting a program from a audio cassette tape deck and a second jack capable of storing a program in a audio cassette tape deck. The main section also has third and fourth jacks which control the operation of the audio cassette tape decks connected to the first two jacks.

Growing community of inventors

Tokyo, Japan

Masao Watari