• The Journal of the Acoustical Society of Korea
• /
• 제15권2E호
• /
• pp.14-23
• /
• 1996

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.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.672-675
• /
• 1999

In this paper, we propose a MLP neural network architecture and feature extraction for Korean syllable recognition. In the proposed syllable recognition system, firstly onset is classified by onset classification neural network. And the results information of onset classification neural network are used for feature selection of imput patterns vector. The feature extraction of Korean syllables is based on sonority. Using the threshold rate separate the syllable. The results of separation are used for feature of onset. nucleus and coda. ETRI's SAMDORI has been used by speech DB. The recognition rate is 96% in the speaker dependent and 93.3% in the speaker independent.

• 한국통신학회논문지
• /
• 제33권9C호
• /
• pp.691-696
• /
• 2008

본 논문은 AMR(Adaptive Multi Rate)코더의 7.4kit/s 모드를 기반으로 화자 의존적인 환경에서 더욱 압축률을 높인 새로운 켈프(CELP)계열의 코더를 제안한다. 제안된 코더는 OGM(OutGoing Message)이나 TTS(Text-To-Speech) 등 한 사람의 음성만을 필요로 하는 시스템에서 유용하게 사용할 수 있다. 새로운 코더의 압축률을 높이기 위해서 무감독 학습 신경망인 Centroid Neural Networks(CNN)를 이용한 새로운 LSP 코드북을 생성하여 사용한다. 또한 고정 코드북 탐색 단계에서 AMR 7.4 kbit/s 모드에서는 4개의 펄스를 서브프레임 마다 사용하는 대신에 새로운 코더에서는 오직 2개의 펄스만을 사용하기 때문에 압축률을 더 높일 수 있다. 이로 인해서 스피치의 질이 감소하게 되는데, 각 서브프레임 마다 예상하는 펄스를 적용함으로써 보상받을 수 있다. 제안된 보코더는 기존 AMR 7.4Kbps모드와 비교해 27% 높은 압축률을 가지는 동시에, MOS( Mean Opinion Score)의 면에서 볼 때, 대등한 음질을 보였다.

• 한국지능시스템학회논문지
• /
• 제18권4호
• /
• pp.494-500
• /
• 2008

휴먼인터페이스 기술의 발달에서 인간과 기계의 상호작용은 중요한 부분이다. 감정인식에 대한 연구는 이러한 상호작용에 도움을 준다. 본 연구는 개인화된 음성신호에 대하여 감정인식 알고리즘을 제안하였다. 감정인식을 위하여 PLP 분석을 이용하여 음성신호의 특징으로 사용하였다. 처음에 PLP 분석은 음성인식에서 음성신호의 화자 종속적인 성분을 제거하기 위하여 사용되었으나 이후 화자인식을 위한 연구에서 PLP 분석이 화자의 특징 추출을 위해 효과적임을 설명하고 있다. 그래서 본 논문은 PLP 분석으로 만들어진 개인화된 감정 패턴을 이용하여 쉽게 실시간으로 음성신호로부터 감정을 평가하는 알고리즘을 제안하였다. 그 결과 최대 90%이상의 인식률과 평균 75%의 인식률을 보였다. 이 시스템은 간단하지만 효율적이다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2010년도 춘계학술대회
• /
• pp.934-937
• /
• 2010

본 논문에서는 물리적 스위치 방식의 인터페이스를 사용하기 불편한 장애우나 전자기기 사용에 익숙하지 못한 사람들을 위한 차세대 인터페이스를 구현하기 위해 음성인식과 3축 가속도센서를 헤드셋과 연동하여 새로운 마우스 포인팅 시스템을 구현하였다. 인식률이 상대적으로 높은 화자종속방식을 지원하고 그 음성신호를 인식해서 BCD 코드로 출력을 내는 음성인식 모듈을 헤드셋의 마이크의 출력부와 연결하여 사용하였으며, TMS320F2812 프로세서를 사용한 컨트롤러를 구축하여 3축 가속도 센서와 연동한 후 헤드셋의 머리윗부분에 장착하여 비주얼 베이직을 통해 헤드셋으로 마우스 포인팅 및 클릭이 가능한 시스템을 구현하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권2호
• /
• pp.149-154
• /
• 2004

In this research, we selected the speech recognition to implement the electric wheelchair system as a method to control it by only using the speech and used DTW (Dynamic Time Warping), which is speaker-dependent and has a relatively high recognition rate among the speech recognitions. However, it has to have small memory and fast process speed performance under consideration of real-time. Thus, we introduced VQ (Vector Quantization) which is widely used as a compression algorithm of speaker-independent recognition, to secure fast recognition and small memory. However, we found that the recognition rate decreased after using VQ. To improve the recognition rate, we applied ART2 (Adaptive Reason Theory 2) algorithm as a post-process algorithm to obtain about 5% recognition rate improvement. To utilize ART2, we have to apply an error range. In case that the subtraction of the first distance from the second distance for each distance obtained to apply DTW is 20 or more, the error range is applied. Likewise, ART2 was applied and we could obtain fast process and high recognition rate. Moreover, since this system is a moving object, the system should be implemented as an embedded one. Thus, we selected TMS320C32 chip, which can process significantly many calculations relatively fast, to implement the embedded system. Considering that the memory is speech, we used 128kbyte-RAM and 64kbyte ROM to save large amount of data. In case of speech input, we used 16-bit stereo audio codec, securing relatively accurate data through high resolution capacity.

• Journal of Information Processing Systems
• /
• 제9권2호
• /
• pp.259-270
• /
• 2013

A speaker's intentions can be represented by domain actions (domain-independent speech act and domain-dependent concept sequence pairs). Therefore, it is essential that domain actions be determined when implementing dialogue systems because a dialogue system should determine users' intentions from their utterances and should create counterpart intentions to the users' intentions. In this paper, a neural network model is proposed for classifying a user's domain actions and planning a system's domain actions. An integrated neural network model is proposed for simultaneously determining user and system domain actions using the same framework. The proposed model performed better than previous non-integrated models in an experiment using a goal-oriented dialogue corpus. This result shows that the proposed integration method contributes to improving domain action determination performance.

• 한국지능시스템학회논문지
• /
• 제14권2호
• /
• pp.201-206
• /
• 2004

This study attempted to develop a speech recognition module applied to a wheelchair for the physically handicapped. In the proposed speech recognition module, TMS320C32 was used as a main processor and Mel-Cepstrum 12 Order was applied to the pro-processor step to increase the recognition rate in a noisy environment. DTW (Dynamic Time Warping) was used and proven to be excellent output for the speaker-dependent recognition part. In order to utilize this algorithm more effectively, the reference data was compressed to 1/12 using vector quantization so as to decrease memory. In this paper, the necessary diverse technology (End-point detection, DMA processing, etc.) was managed so as to utilize the speech recognition system in real time

• 한국멀티미디어학회논문지
• /
• 제22권8호
• /
• pp.852-859
• /
• 2019

With the development of IT technology and smart devices, various applications utilizing image information are being developed. In order to provide an intuitive interface for pronunciation recognition, there is a growing need for research on pronunciation recognition using mouth feature values. In this paper, we propose a system to distinguish Korean vowel pronunciations by detecting feature points of lips region in images and applying Bayesian based learning model. The proposed system implements the recognition system based on Bayes' theorem, so that it is possible to improve the accuracy of speech recognition by accumulating input data regardless of whether it is speaker independent or dependent on small amount of learning data. Experimental results show that it is possible to effectively distinguish Korean vowels as a result of applying probability based Bayesian classification using only visual information such as mouth shape features.

• 한국음향학회지
• /
• 제14권3호
• /
• pp.97-104
• /
• 1995

본 논문은 음성 다이얼링 시스템 구현을 위한 연속 숫자음 인식에 관한 연구로써, 구문 분석을 이용한 One-Stage DP에 의한 음성 인식 방법을 제안하다. 인식 실험을 위해 우선 구간 구분화 알고리즘을 이용하여 DMS (Dynamic Multi-SEction) 모델을 만들며, 제안된 구문 분석을 이용한 One-Stage DP 방법으로 실험 대ㅛ상의 연속 숫자음 데이터를 인식하게 하였다. 본 연구에서는 8명의 ㅣ남성 화자에 의해 2-3번 발음도니 21종의 7자리의 연속 숫자음이 사용되었고, 기존의 One-Stage DP와 제안된 구문 분석을 이용한 One-Stage DP 음성 인식 알고리즘을 사용해서 화자 종속과 화자 독립 실험을 실험실 환경에서 수행하였다. 인식 실험 결과, 기존의 방법보다 제안된 방법이 인식률이 좋은 것으로 나타났으며, 제안된 방법에서는 화자 종속과 화자 독립 실험에서 각각 약 91.7%, 89.7%로 나타났다.