지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
초록· 키워드
오류제보하기
This paper is a on the neural network to recognize the phonemes, the weight initialization to reduce learning speed, and LR parser for continuous speech recognition. The neural network spots the phonemes in continuous speech and LR parser parses the output of neural network. The whole phonemes recognized in neural network are divided into several groups which are grouped by the similarity of phonemes, and then each group consists of neural network. Each group of neural network to recognize the phonemes consisits of that recognize the phonemes of their own group and VGNN(Verify Group Neural Network) which judges whether the inputs are their own group or not. The weights of neural network are not initialized with random values but initialized from learning data to reduce learning speed. The LR parsing method applied to this paper is not a method which traces a unique path, but one which traces several possible paths because the output of neural network is not accurate. The parser processes the continuous speech frame by frame as accumulating the output of neural network through several possible paths. If this accumulated path-value drops below the threshold value, this path is deleted in possible parsing paths. This paper applies the continuous speech recognition system to the threshold value, this path is deleted in possible parsing paths. This paper applies the continuous speech recognition system to the continuous Korea digits recognition. The recognition rate of isolated digits is 97% in speaker dependent, and 75% in speaker dependent. The recognition rate of continuous digits is 74% in spaker dependent.
목차
등록된 정보가 없습니다.
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
A Korean Phoneme Recognition system using Neural Networks
대한전자공학회 기타 간행물
1992 .01
-
Phoneme Recognition based on Two-Layered Stereo Vision Neural Network
멀티미디어학회논문지
2002 .10
-
음소경계 정보를 이용한 한국어 숫자음 인식에 관한 연구
한국음향학회 학술발표대회
2001 .01
-
A New Approach to Simultaneous Phoneme Segmentation and Recognition Continuous Speech
ICONIP : International Conference On Neural Information Processing
1994 .01
-
A STUDY ON SPEECH SYNTHESIS USING NEURAL NETWORK
JTC-CSCC : Joint Technical Conference on Circuits Systems, Computers and Communications
1992 .01
-
Identification of Continuous Systems Using Neural Network
제어로봇시스템학회 국내학술대회 논문집
1992 .10
-
A Prototype System for Continuous Speech Recognition using Group Training Based on Neural Networks
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
1997 .01
-
음성 인식을 위한 Fuzzy와 Neural Network의 적용 ( The Application of Fuzzy and Neural Network for Speech Recognition )
대한전자공학회 학술대회
1991 .11
-
A Study on Korean Voice Recognition Using the Neural Network
JTC-CSCC : Joint Technical Conference on Circuits Systems, Computers and Communications
1991 .01
-
Speech Recognition by Neural Net Pattern Recognition Equations with Self-organization
한국음향학회지
2003 .01
-
PATTERNS RECOGNITION VIA ARTIFICIAL NEURAL NETWORK SYSTEMS
제어로봇시스템학회 국내학술대회 논문집
1990 .10
-
연속 숫자음 인식을 위한 신경망에 관한 연구
대한전자공학회 학술대회
1995 .12
-
연속 숫자음 인식을 위한 신경망에 관한 연구 ( A Study on the Neural for Korean Continuous Digit Recognition )
대한전자공학회 학술대회
1995 .11
-
Self-Normalizing Neural Network 를 이용한 동작 패턴 인식의 향상
한국정밀공학회 학술발표대회 논문집
2018 .05
-
Neural Network에 의한 숫자인식에 관한 연구 ( A Study on Numeral Data Recognition using Neural Network )
대한전자공학회 학술대회
1989 .07
-
신경회로망을 이용한 직류전동기의 센서리스 속도제어
Journal of Advanced Marine Engineering and Technology (JAMET)
2004 .01
-
Emotional Recognition of speech signal using Recurrent Neural Network
제어로봇시스템학회 국제학술대회 논문집
2002 .10
-
Identification of Continuous Systems Using Neural Network
대한전자공학회 학술대회
1992 .10
-
Stereo Vision Neural Networks with Competition and Cooperation for Phoneme Recognition
한국음향학회지
2003 .01
-
Fire detection using neural network
제어로봇시스템학회 국제학술대회 논문집
2006 .10
이 논문의 저자 정보
최근 본 자료
댓글(0)
0