• 대한음성학회지:말소리
• /
• 제64호
• /
• pp.121-135
• /
• 2007

Speech signal is distorted by channel characteristics or additive noise and then the performances of speaker or speech recognition are severely degraded. To cope with the noise problem, we propose a modified HMM decoder algorithm using SNR-based observation confidence, which was successfully applied for GMM in speaker identification task. The modification is done by weighting observation probabilities with reliability values obtained from SNR. Also, we apply PSO (particle swarm optimization) method to the confidence function for maximizing the speaker identification performance. To evaluate our proposed method, we used the ETRI database for speaker recognition. The experimental results showed that the performance was definitely enhanced with the modified HMM decoder algorithm.

• 음성과학
• /
• 제8권3호
• /
• pp.93-104
• /
• 2001

The author analyzed acoustic parameters of ten Korean numbers produced by ten male students using Praat. Variations of f0, F1, F2 and F3 within and between speakers were examined by determining an average and standard deviation of the parameters of each number and by comparing the acoustic values with one another. Results showed that each subject produced the numbers within a certain range of variation across time. Thus, speaker identification can be more certain using dynamic information of the acoustic parameters within each vocalic segment. Also, percent difference of within-subjects' variation to that of between-subjects can be utilized to determine which sounds would be better stimuli for speaker identification. According to the criteria, the number '2' proved the best stimulus while the number '7' was the worst. Future studies will be necessary to explore robust methods of speaker identification under noisy conditions.

• 한국음향학회지
• /
• 제8권4호
• /
• pp.65-73
• /
• 1989

본 연구에서는, VQ(vector quantization)와 모음 인식에 기초한 화자 인식 알고리즘을 제안하고, 기존의 VQ를 사용한 화자 인식 알고리즘과 성능을 비교하였다. 제안된 화자 인식 알고리즘은 모음 분리, 모음 인식 그리고 평균 distortion양을 계산하는 3개의 과정으로 구성되며, 이때 주어진 음성 신호로부터 모음 부분을 분리하기 위해 RMS 에너지, BTR(Back-to-Total cavity volume Ratio) 그리고 SFBR(Signed-Front-to-Back maximum area Ratio)이 라는 3개 의 Parameter를 사용하였다. 입력 음성 신호의 SNR이 20 dB이고 정확한 모음 분리가 수행되었을 때, 제안된 화자 인식 알고리즘의 성능이 기존의VQ를 사용한 화자 인식 알고리즘의 성능보다 대체로 좋았으며, 입력 신호가 전화선을 통과한 신호이고 잡음이 있는 경우에도 유사한 결과를 얻을 수 있었다

• 음성과학
• /
• 제10권4호
• /
• pp.159-166
• /
• 2003

To reduce the high dimensionality required for training of feature vectors in speaker identification, we propose an efficient GMM based on local PCA with Fuzzy clustering. The proposed method firstly partitions the data space into several disjoint clusters by fuzzy clustering, and then performs PCA using the fuzzy covariance matrix in each cluster. Finally, the GMM for speaker is obtained from the transformed feature vectors with reduced dimension in each cluster. Compared to the conventional GMM with diagonal covariance matrix, the proposed method needs less storage and shows faster result, under the same performance.

• 음성과학
• /
• 제12권2호
• /
• pp.171-182
• /
• 2005

An efficient GMM (Gaussian mixture modeling) method based on LPCA (local principal component analysis) with VQ (vector quantization) for speaker identification is proposed. To reduce the dimension and correlation of the feature vector, this paper proposes a speaker identification method based on principal component analysis. The proposed method firstly partitions the data space into several disjoint regions by VQ, and then performs PCA in each region. Finally, the GMM for the speaker is obtained from the transformed feature vectors in each region. Compared to the conventional GMM method with diagonal covariance matrix, the proposed method requires less storage and complexity while maintaining the same performance requires less storage and shows faster results.

• 음성과학
• /
• 제11권2호
• /
• pp.237-245
• /
• 2004

In general, Gaussian mixture model(GMM) is used to estimate the speaker model for speaker identification. The parameter estimates of the GMM are obtained by using the expectation-maximization (EM) algorithm for the maximum likelihood(ML) estimation. However, if the number of mixtures isn't defined well in the GMM, those parameters are obtained inappropriately. The problem to find the number of components is significant to estimate the optimal parameter in mixture model. In this paper, to estimate the optimal number of mixtures, we propose the method that starts from the sufficient mixtures, after, the number is reduced by investigating the mutual information between mixtures for GMM. In result, we can estimate the optimal number of mixtures. The effectiveness of the proposed method is shown by the experiment using artificial data. Also, we performed the speaker identification applying the proposed method comparing with other approaches.

• 음성과학
• /
• 제7권3호
• /
• pp.185-195
• /
• 2000

This paper seeks to compare the feature parameters used in speaker identification systems under noisy environments. The feature parameters compared are LP cepstrum (LPCC), Cepstral mean subtraction(CMS), Pole-filtered CMS(PFCMS), Adaptive component weighted cepstrum(ACW) and Postfilter cepstrum(PF). The GMM-based text independent speaker identification system is designed for this target. Some series of experiments show that the LPCC parameter is adequate for modelling the speaker in the matched environments between train and test stages. But in the mismatched training and testing conditions, modified parameters are preferable the LPCC. Especially CMS and PFCMS parameters are more effective for the microphone mismatching conditions while the ACW and PF parameters are good for more noisy mismatches.

• 말소리와 음성과학
• /
• 제1권1호
• /
• pp.69-73
• /
• 2009

This paper proposes an efficient global covariance-based principal component analysis (GCPCA) for speaker identification. Principal component analysis (PCA) is a feature extraction method which reduces the dimension of the feature vectors and the correlation among the feature vectors by projecting the original feature space into a small subspace through a transformation. However, it requires a larger amount of training data when performing PCA to find the eigenvalue and eigenvector matrix using the full covariance matrix by each speaker. The proposed method first calculates the global covariance matrix using training data of all speakers. It then finds the eigenvalue matrix and the corresponding eigenvector matrix from the global covariance matrix. Compared to conventional PCA and Gaussian mixture model (GMM) methods, the proposed method shows better performance while requiring less storage space and complexity in speaker identification.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.928-940
• /
• 2017

State-of-the-art speaker recognition systems may work better for the English language. However, if the same system is used for recognizing those who speak different languages, the systems may yield a poor performance. In this work, the decisions of a Gaussian mixture model-universal background model (GMM-UBM) and a learning vector quantization (LVQ) are combined to improve the recognition performance of a multilingual speaker identification system. The difference between these classifiers is in their modeling techniques. The former one is based on probabilistic approach and the latter one is based on the fine-tuning of neurons. Since the approaches are different, each modeling technique identifies different sets of speakers for the same database set. Therefore, the decisions of the classifiers may be used to improve the performance. In this study, multitaper mel-frequency cepstral coefficients (MFCCs) are used as the features and the monolingual and cross-lingual speaker identification studies are conducted using NIST-2003 and our own database. The experimental results show that the combined system improves the performance by nearly 10% compared with that of the individual classifier.

• 한국산학기술학회논문지
• /
• 제12권5호
• /
• pp.2402-2409
• /
• 2011

음성에는 전달하고자 하는 정보 이외에 화자 고유의 음향적 특징을 담고 있다. 화자간의 음향적 차이를 이용하여 말하고 있는 사람이 누구인지 판단하는 방법이 화자 인식이다. 화자 인식에는 화자 확인과 화자 식별로 구분되는데 화자 확인은 1명의 음성을 대상으로 본인인지 아닌지를 검증하는 방법이다. 반면, 화자 식별은 미리 등록된 다수의 종속 문장으로부터 가장 유사한 모델을 찾아 대상 의뢰인이 누군지 식별하는 방법이다. 본 논문에서는 MFCC(Mel Frequency Cepstral Coefficient) 계수를 추출하여 특징 벡터를 구성하였고, 특징 간 유사도 비교는 동적 시간 신축(Dynamic Time Warping) 알고리즘을 이용한다. 각 화자마다 두 개의 종속 문장을 훈련 데이터로 사용하여 음운성에 기반을 둔 공통적 특징을 기술하였고, 이를 통해 데이터베이스에 저장되어 있지 않은 단어를 사용하더라도 동일 화자임을 식별할 수 있도록 하였다.