KR100301596B1 - Method of studying and recognizing word in voice recognition system - Google Patents

Method of studying and recognizing word in voice recognition system Download PDF

Info

Publication number
KR100301596B1
KR100301596B1 KR1019970076306A KR19970076306A KR100301596B1 KR 100301596 B1 KR100301596 B1 KR 100301596B1 KR 1019970076306 A KR1019970076306 A KR 1019970076306A KR 19970076306 A KR19970076306 A KR 19970076306A KR 100301596 B1 KR100301596 B1 KR 100301596B1
Authority
KR
South Korea
Prior art keywords
model
word
voice recognition
studying
sections
Prior art date
Application number
KR1019970076306A
Other languages
Korean (ko)
Other versions
KR19990056312A (en
Inventor
Nam Ho Jung
O Il Kwon
Seong Hui Park
Original Assignee
Hyundai Autonet Co 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 Hyundai Autonet Co Ltd filed Critical Hyundai Autonet Co Ltd
Priority to KR1019970076306A priority Critical patent/KR100301596B1/en
Priority to JP10367759A priority patent/JPH11352982A/en
Publication of KR19990056312A publication Critical patent/KR19990056312A/en
Application granted granted Critical
Publication of KR100301596B1 publication Critical patent/KR100301596B1/en

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
    • G10L2019/0001—Codebooks
    • G10L2019/0002—Codebook adaptations

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Algebra (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Machine Translation (AREA)
  • Character Discrimination (AREA)

Abstract

PURPOSE: A method of studying and recognizing a word in a voice recognition system is provided to improve voice recognition rate in a speaker independent system and a speaker dependent system. CONSTITUTION: Study data is divided into sections at an equal interval(S10). Vectors of the same sections are grouped(S11). A codeword is calculated to form a code book, and the average length of each section is calculated to form a word model(S12). The word model is compared with the previous model(S13). Pattern matching is performed between new model study patterns until the word model becomes identical to the previous model(S16). Sections of the study patterns are redivided, and the word model is stored in a database(S17).
KR1019970076306A 1997-12-29 1997-12-29 Method of studying and recognizing word in voice recognition system KR100301596B1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
KR1019970076306A KR100301596B1 (en) 1997-12-29 1997-12-29 Method of studying and recognizing word in voice recognition system
JP10367759A JPH11352982A (en) 1997-12-29 1998-12-24 Word learning and recognizing method in voice recognizing system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019970076306A KR100301596B1 (en) 1997-12-29 1997-12-29 Method of studying and recognizing word in voice recognition system

Publications (2)

Publication Number Publication Date
KR19990056312A KR19990056312A (en) 1999-07-15
KR100301596B1 true KR100301596B1 (en) 2001-06-26

Family

ID=19529205

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019970076306A KR100301596B1 (en) 1997-12-29 1997-12-29 Method of studying and recognizing word in voice recognition system

Country Status (2)

Country Link
JP (1) JPH11352982A (en)
KR (1) KR100301596B1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8812317B2 (en) 2009-01-14 2014-08-19 Samsung Electronics Co., Ltd. Signal processing apparatus capable of learning a voice command which is unsuccessfully recognized and method of recognizing a voice command thereof

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8812317B2 (en) 2009-01-14 2014-08-19 Samsung Electronics Co., Ltd. Signal processing apparatus capable of learning a voice command which is unsuccessfully recognized and method of recognizing a voice command thereof

Also Published As

Publication number Publication date
KR19990056312A (en) 1999-07-15
JPH11352982A (en) 1999-12-24

Similar Documents

Publication Publication Date Title
Katagiri et al. New discriminative training algorithms based on the generalized probabilistic descent method
CA2315832A1 (en) System for using silence in speech recognition
DE69925932D1 (en) LANGUAGE SYNTHESIS BY CHAINING LANGUAGE SHAPES
DE60123952D1 (en) GENERATION OF A UNIFORM TASK DEPENDENT LANGUAGE MODEL THROUGH INFORMATION DISCUSSION PROCESS
DE69818231D1 (en) METHOD FOR THE DISCRIMINATIVE TRAINING OF VOICE RECOGNITION MODELS
ATE258332T1 (en) NETWORK AND VOICE MODELS FOR USE IN A VOICE RECOGNITION SYSTEM
ATE176546T1 (en) VOICE ACTIVE SERVICE
WO2002080139A3 (en) Method and apparatus for voice dictation and document production
JPS5629292A (en) Continuous voice identifier
CA2228948A1 (en) Pattern recognition
EP1071073A3 (en) Dictionary organizing method for variable context speech synthesis
EP0869478A3 (en) Speech recognition method and apparatus
FI20010792A0 (en) Organizing user-independent speech recognition
EP0764319A4 (en) Method, apparatus, and radio for optimizing hidden markov model speech recognition
BR0313706A (en) Method to process telephone number within audio stream, and wireless communication device
ATE186150T1 (en) VOICE RECOGNITION BASED ON ''HMMS''
GB2233137B (en) Methods for forming registered voice patterns for use in pattern comparison in pattern recognition
ATE122171T1 (en) VOICE RECOGNITION.
KR100301596B1 (en) Method of studying and recognizing word in voice recognition system
JPS64996A (en) Voice recognition system using vector quantization
ATE263997T1 (en) BETWEEN-WORDS CONNECTION PHONEMIC MODELS
SE9802990D0 (en) A method and a system for speech recognition
TW355233B (en) Method and recognizer for recognizing tonal acoustic sound signals
CA2151330A1 (en) A speech recognizer
ES8708266A1 (en) Individual recognition by voice analysis.

Legal Events

Date Code Title Description
A201 Request for examination
N231 Notification of change of applicant
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20130530

Year of fee payment: 13

FPAY Annual fee payment

Payment date: 20140515

Year of fee payment: 14

FPAY Annual fee payment

Payment date: 20150512

Year of fee payment: 15

FPAY Annual fee payment

Payment date: 20160518

Year of fee payment: 16

LAPS Lapse due to unpaid annual fee