KR930014265A - Voice registration and recognition method of voice recognition device - Google Patents

Voice registration and recognition method of voice recognition device Download PDF

Info

Publication number
KR930014265A
KR930014265A KR1019910024619A KR910024619A KR930014265A KR 930014265 A KR930014265 A KR 930014265A KR 1019910024619 A KR1019910024619 A KR 1019910024619A KR 910024619 A KR910024619 A KR 910024619A KR 930014265 A KR930014265 A KR 930014265A
Authority
KR
South Korea
Prior art keywords
voice
signal
converting
pronunciation
recognition
Prior art date
Application number
KR1019910024619A
Other languages
Korean (ko)
Other versions
KR940005044B1 (en
Inventor
한석진
Original Assignee
이헌조
주식회사 금성사
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 이헌조, 주식회사 금성사 filed Critical 이헌조
Priority to KR1019910024619A priority Critical patent/KR940005044B1/en
Publication of KR930014265A publication Critical patent/KR930014265A/en
Application granted granted Critical
Publication of KR940005044B1 publication Critical patent/KR940005044B1/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
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Electrically Operated Instructional Devices (AREA)
  • Telephonic Communication Services (AREA)

Abstract

한번 발음으로 음성을 등록시켜 음성등록 과정이 간편해지도록한 음성인식기긱의 음성등록 및 인식방법에 관한 것으로, 종래에는 한단어를 등록하는데 세번의 발음을 해야했으며 세번발음중 한번이라도 에러가 발생하면 다시 세번 발음해야하는 번거로움이 발생하는 결점이 있었으나 본 발명에서는 한번 발음으로 세번 발음하도록 하는 저장부(6)를 설정하여 상기 결점을 개선시킬 수 있다.It is related to the voice registration and recognition method of the voice recognition device that makes the voice registration process simple by registering the voice with one pronunciation. Conventionally, three pronunciations have to be registered to register a single word. There is a drawback that the trouble of having to pronounce three times occurs, but in the present invention, the defect can be improved by setting the storage unit 6 to pronounce the pronunciation three times.

Description

음성인식 기기의 음성등록 및 인식방법Voice registration and recognition method of voice recognition device

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음As this is a public information case, the full text was not included.

제4도는 본 발명 음성인식 기기의 음성등록 및 인식을 나타낸 블럭도.4 is a block diagram showing voice registration and recognition of the present invention.

제5도는 제4도체 따른 음성등록 모드시의 동작 흐름도.Fig. 5 is a flowchart of operation in the voice registration mode according to the fourth conductor.

제6도는 제4도에 따른 음성인식 모드의 동작 흐름도.6 is an operation flowchart of a voice recognition mode according to FIG.

Claims (2)

입력된 음성신호를 증폭하여 디지탈 신호로 변환시켜 저장하는 동시에 상기 음성신호를 첫번째 발음으로 발생하는 단계와, 상기 저장된 신호를 원래 음성신호로 변환시켜 두번째 발음으로 발생하고 상기 두발음이 유사하면 상기 저장된 신호를 원래 음성신호로 변환시켜 세번째 발음으로 발생하는 단계와 상기 첫번째 내지 세번째 발음이 모두 유사하면 음성신호중 특징있는 부분을 일정디지탈 데이타로 변환시켜 저장하며 음성등록이 되었음을 표시하는 단계를 차례로 실시하여서 이루어지는 음성인식 기기의 음성등록방법.Amplifying the input voice signal, converting the digital signal into a digital signal, and storing the same, and simultaneously generating the voice signal with the first pronunciation; converting the stored signal into the original voice signal with the second pronunciation; Converting the signal into the original voice signal to generate the third pronunciation and if the first to third pronunciations are similar, converting and storing the characteristic part of the voice signal into digital data and indicating that the voice is registered. Voice registration method of voice recognition device. 입력된 음성신호를 디지탈신호로 변환하여 저장하며 상기 음성신호의 특징을 디지탈신호로 추출해서 미리 등록되어 있는 디지탈로된 신호들과 비교하는 단계와, 상기 비교후 추출된 디지탈신호와 가장 유사한 신호의 번호를 발생하며 인식완료가 되었음을 표시하는 단계를 차례로 실시하여서 이루어지는 음성인식 기기의 음성인식방법.Converting and storing the input voice signal into a digital signal, and extracting a feature of the voice signal into a digital signal and comparing the digital signal with a pre-registered digital signal; A voice recognition method of a voice recognition device, which is performed by sequentially generating a number and indicating that recognition is completed. ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019910024619A 1991-12-27 1991-12-27 Voice recognizing apparatus and voice recording method KR940005044B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019910024619A KR940005044B1 (en) 1991-12-27 1991-12-27 Voice recognizing apparatus and voice recording method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019910024619A KR940005044B1 (en) 1991-12-27 1991-12-27 Voice recognizing apparatus and voice recording method

Publications (2)

Publication Number Publication Date
KR930014265A true KR930014265A (en) 1993-07-22
KR940005044B1 KR940005044B1 (en) 1994-06-10

Family

ID=19326231

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019910024619A KR940005044B1 (en) 1991-12-27 1991-12-27 Voice recognizing apparatus and voice recording method

Country Status (1)

Country Link
KR (1) KR940005044B1 (en)

Also Published As

Publication number Publication date
KR940005044B1 (en) 1994-06-10

Similar Documents

Publication Publication Date Title
KR0135975B1 (en) Text processing system
JPS64720B2 (en)
De Mori A descriptive technique for automatic speech recognition
KR930014265A (en) Voice registration and recognition method of voice recognition device
JPS63149699A (en) Voice input/output device
JPS6083136A (en) Program reader
JP2612030B2 (en) Text-to-speech device
JP2004139530A (en) Reading correction program
JPS6232798B2 (en)
JPS60188995A (en) Sentence enunciation
JP3031081B2 (en) Voice recognition device
TW444161B (en) Method and system providing similar code of character option
JPH064598A (en) Information storage retriever
KR100317215B1 (en) Device and method for recording speaker independent and vocabulary independent voice model using phonem like unit
JPH04218871A (en) Electronic translator provided with sounding function
JPS6349799A (en) Voice output device
JPH0535441A (en) Automatic document preparing device
JPS6344700A (en) Word detection system
JPH06175576A (en) Chinese language learning device
KR930014261A (en) Speech Rule Synthesis LSI Device
JPS6344696A (en) Word detection system
JPS6344698A (en) Word detection system
JPH0375898B2 (en)
JPS6242200A (en) Voice recognition equipment
JPH06161486A (en) Language recognizing and speech output device

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
G160 Decision to publish patent application
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 19980325

Year of fee payment: 5

LAPS Lapse due to unpaid annual fee