• 대한전자공학회논문지
• /
• 제27권12호
• /
• pp.1933-1939
• /
• 1990

In this paper, we proposed an algorithm which used backtracking method to get time information, and it be modelled DMS (Dynamic Multisection) by feature vectors and time information whic are represented to similiar feature in word patterns spoken during continuous time domain, for Korean Speech recognition by independent speaker using DMS. Each state of model is represented time sequence, and have time information and feature vector. Typical feature vector is determined as the feature vector of each state to minimize the distance between word patterns. DDD Area names are selected as recognition wcabulary and 12th LPC cepstrum coefficients are used as the feature parameter. State of model is made 8 multisection and is used 0.2 as weight for time information. Through the experiment result, recognition rate by DMS model is 94.8%, and it is shown that this is better than recognition rate (89.3%) by MSVQ(Multisection Vector Quantization) method.

• 전자공학회논문지B
• /
• 제30B권3호
• /
• pp.1-9
• /
• 1993

This paper discusses issues on the disign and implementation of real-time automatic speaker verification system, as well as the performance analysis of the implemented system. The system employs TI's TMS320C25 digital signal processor TMS320C25 and high speed SRAMs. The system is designed to be used stand-alone as well as via hand-shaking with IBM-PC. The speech parameters used for speaker verification are PARCOR and LPC-cepstrum coefficients, and the employed decision logics are those based on the generalized weighted distance comcept. The implemented system showed the performance of 5.3% error rate for the PARCOR coefficient, and 4.7% error rate for the LPG-cepstrum coefficient.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 10월 학술대회지
• /
• pp.101-104
• /
• 2003

In this paper, speech quality is improved by removing abrupt noise intervals and then substituting the gaps with estimates of the previous speech waveform. An abrupt noise detection signal has been proposed as a prediction error signal by utilizing LP coefficients of the previous frame. Abrupt noise intervals are estimated by using spectral energy. After removing estimated noise intervals, we applied several waveform substitution techniques such as zero substitution, previous frame repetition, pattern matching, and pitch waveform replication. To prove the validity of our algorithm, the LPC spectral distortion test and the recognition test are executed and, the results show that the speech quality is fairly well improved.

• 전자공학회논문지S
• /
• 제34S권4호
• /
• pp.57-65
• /
• 1997

The purpose of this paper is to propose the HMM (hidden markov model) based on multi-observation sequence for the isolated word recognition. The proosed model generates the codebook of MSVQ by dividing each word into several sections followed by dividing training data into several sections. Then, we are to obtain the sequential value of multi-observation per each section by weighting the vectors of distance form lower values to higher ones. Thereafter, this the sequential with high probability value while in recognition. 146 DDD area names are selected as the vocabularies for the target recognition, and 10LPC cepstrum coefficients are used as the feature parameters. Besides the speech recognition experiments by way of the proposed model, for the comparison with it, the experiments by DP, MSVQ, and genral HMM are made with the same data under the same condition. The experiment results have shown that HMM based on multi-observation sequence proposed in this paper is proved superior to any other methods such as the ones using DP, MSVQ and general HMM models in recognition rate and time.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 제39회 하계학술대회
• /
• pp.2255-2256
• /
• 2008

음성인식 시스템을 설계함에 있어서는 대표적으로 사람의 성도 특성을 모방한 LPC(Linear Predict Cording)방식과 청각 특성을 고려한 MFCC(Mel-Frequency Cepstral Coefficients)방식이 있다. 본 논문에서는 MFCC를 통해 특징파라미터를 추출하고 해당 영역에서의 수행된 작업을 매틀랩 알고리즘을 이용하여 그래프로 시현하였다. MFCC 방식의 추출과정은 최초의 음성신호로부터 전처리과정을 통해 아날로그 신호를 디지털 신호로 변환하고, 잡음부분을 최소화하며, 음성 부분을 강조한다. 이 신호는 다시 Windowing을 통해 음성의 불연속을 제거해 주고, FFT를 통해 시간의 영역을 주파수의 영역으로 변환한다. 이 변환된 신호는 Filter Bank를 거쳐 다수의 복잡한 신호를 몇 개의 간단한 신호로 간소화 할 수 있으며, 마지막으로 Mel-cepstrum을 통해 최종적으로 특징 파라미터를 얻고자 하였다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제51권2호
• /
• pp.69-77
• /
• 2002

Speaker verification can be classified in two categories, text-dependent speaker verification and text-independent speaker verification. In this paper, we discuss text-dependent speaker verification. Text-dependent speaker verification system determines whether the sound characteristics of the speaker are equal to those of the specific person or not. In this paper we obtain the speaker data using a sound card in various noisy conditions, apply a new Hidden LMS (Least Mean Square) adaptive algorithm to it, and extract LPC (Linear Predictive Coding)-cepstrum coefficients as feature vectors. Finally, we use a competitive learning neural network for speaker verification. The proposed hidden LMS adaptive filter using a neural network reduces noise and enhances features in various noisy conditions. We construct a separate neural network for each speaker, which makes it unnecessary to train the whole network for a new added speaker and makes the system expansion easy. We experimentally prove that the proposed method improves the speaker verification performance.

• 감성과학
• /
• 제8권1호
• /
• pp.1-7
• /
• 2005

This paper reports several emotion detecting methods based on various attributes of human voice. These methods have been developed at our Engineering Systems Laboratory. It is noted that, in all of the proposed methods, only prosodic information in voice is used for emotion recognition and semantic information in voice is not used. Different types of neural networks(NNs) are used for detection depending on the type of voice parameters. Earlier approaches separately used linear prediction coefficients(LPCs) and time series data of pitch but they were combined in later studies. The proposed methods are explained first and then evaluation experiments of individual methods and their performances in emotion detection are presented and compared.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1990년도 춘계학술대회
• /
• pp.73-78
• /
• 1990

In this study, LPC cepstrum coefficients are used as feature vector extracted from AR model of EMG signal, and a reduced-connection network which has reduced connection between nodes is constructed to classify and recognize EMG functional classes. The proposed network reduces learning time and improves system stability. Therefore it is shown that the proposed network is appropriate in recognizing the function of EMG signal.

• 한국음향학회지
• /
• 제6권1호
• /
• pp.23-28
• /
• 1987

본 연구에서는 집단화 알고리즘을 이용하여 한국어 단독음의 표준 패턴을 설정하였다. Minimax기법을 이용하여 각 단독음에 대하여 최고 3개까지 표준패턴을 설정하여 인식하였다. 특징 파라미터는 선형예측계수와 자기 상관 계수를 이용하였으며 패턴들 간의 유사도 비교는 Itakura가 제안한 거리측정법을 이용하였다. 표준패턴을 1개만 설정하였을 때 $55.9\%$, 2개를 설정했을 때 $76.9\%$, 3개를 설정했을 경우는 $89.5\%$의 인식률을 얻었다.

• 대한전자공학회논문지
• /
• 제24권5호
• /
• pp.905-913
• /
• 1987

This paper presents a speaker dependent isolated digit recognition algorithm using the Mellin transform. Since the Mellin transform converts a scale information into a phase information, attempts have been made to utilize this scale invariance property of the Mellin transform in order to alleviate a time-normalization procedure required for a speech recognition. It has been found that good results can be obtained by taking the Mellin transform to the features such as a ZCR, log energy, normalized autocorrelation coefficients, first predictor coefficient and normalized prediction error. We employed a difference function for evaluating a similarity between two patterns. When the proposed algorithm was tested on Korean digit words, a recognition rate of 83.3% was obtained. The recognition accuracy is not compatible with the other technique such as LPC distance however, it is believed that the Mellin transform can effectively perform the time-normalization processing for the speech recognition.