JPS56162183A - Pattern matching method - Google Patents

Pattern matching method

Info

Publication number
JPS56162183A
JPS56162183A JP6410680A JP6410680A JPS56162183A JP S56162183 A JPS56162183 A JP S56162183A JP 6410680 A JP6410680 A JP 6410680A JP 6410680 A JP6410680 A JP 6410680A JP S56162183 A JPS56162183 A JP S56162183A
Authority
JP
Japan
Prior art keywords
stored
spectrum information
memory
resemblance
expression
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP6410680A
Other languages
Japanese (ja)
Inventor
Akira Ichikawa
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Priority to JP6410680A priority Critical patent/JPS56162183A/en
Publication of JPS56162183A publication Critical patent/JPS56162183A/en
Pending legal-status Critical Current

Links

Landscapes

  • Character Discrimination (AREA)

Abstract

PURPOSE: To recognize a voice sequence pattern efficiently with a high precision, by masking an optional part of standard patterns and appreciating the degree of resemblance to an unknown pattern through performing matching.
CONSTITUTION: An input voice signal 2 corresponding to an unknown pattern is converted to spectrum information through an A/D converter 3 and a BPF4 and is stored in a prescribed area of main memory 5. The degree of resemblance between spectrum information in the i-th frame writtem already and spectrum information in the j-th frame of standard patterns registered in a memory 6 is calculated by the expression 2. The operation of the expression 1 is executed on a basis of this di,j prescribed constants DOPT and LOPT stored in the main memory 5 and a weight quantity Wj stored in the memory 6, by a main control part 1 to obtain Si,j. Thus, through masking corresponding to the value of the weight Wj and matching are perfromed to extract vowel and consonant sequences from the input voice, and a code 14 corresponding to them is transmitted from an output part 15.
COPYRIGHT: (C)1981,JPO&Japio
JP6410680A 1980-05-16 1980-05-16 Pattern matching method Pending JPS56162183A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP6410680A JPS56162183A (en) 1980-05-16 1980-05-16 Pattern matching method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP6410680A JPS56162183A (en) 1980-05-16 1980-05-16 Pattern matching method

Publications (1)

Publication Number Publication Date
JPS56162183A true JPS56162183A (en) 1981-12-12

Family

ID=13248483

Family Applications (1)

Application Number Title Priority Date Filing Date
JP6410680A Pending JPS56162183A (en) 1980-05-16 1980-05-16 Pattern matching method

Country Status (1)

Country Link
JP (1) JPS56162183A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4471453A (en) * 1980-09-20 1984-09-11 U.S. Philips Corporation Measuring mis-match between signals
EP0125422A1 (en) * 1983-04-13 1984-11-21 Texas Instruments Incorporated Speaker-independent word recognizer

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4471453A (en) * 1980-09-20 1984-09-11 U.S. Philips Corporation Measuring mis-match between signals
EP0125422A1 (en) * 1983-04-13 1984-11-21 Texas Instruments Incorporated Speaker-independent word recognizer

Similar Documents

Publication Publication Date Title
DE68928097D1 (en) Speech recognition system
JPS5629299A (en) Voice identifier
JPS5632197A (en) Electronic language converter
EP0321410A3 (en) Method and apparatus for constructing markov model word baseforms
DE3685324D1 (en) DIGITAL VOICE PROCESSOR USING Arbitrary Excitation Coding.
JPS53114601A (en) Voice recognition system
GB8723297D0 (en) Pattern comparison in pattern recognition
JPS56162183A (en) Pattern matching method
JPS54139356A (en) Kana-chinese character converter
CA2056294A1 (en) High speed recognition of a string of words connected according to a regular grammar by dp matching
DE3378384D1 (en) Recognition of continuous speech
SE9303902D0 (en) Device and method of speech synthesis
DE3681023D1 (en) DEVICE AND METHOD FOR VOICE RECOGNITION USING STATISTICAL WORD PATTERNS.
ATE227860T1 (en) ASSOCIATIVE NEURON IN AN ARTIFICIAL NEURAL NETWORK
JPS5292433A (en) Letter output control circuit
JPS52114257A (en) Encoder device
JPS5699582A (en) Word recognizing device
JPS641055A (en) Japanese language processor
JPS57131585A (en) Typewriter
JPS6462700A (en) Voice recognition equipment
JPS5759288A (en) Character recognition device
JPS5619177A (en) Character reader
Caelen et al. Structuralization of acoustic information in the A. R. I. A. L. project.).
JPS5567863A (en) Electronic computer
JPS56111378A (en) Analog control mechanism