• 한국정보과학회논문지:소프트웨어및응용
• /
• 제27권5호
• /
• pp.583-592
• /
• 2000

본 논문에서는 독립성분분석을 이용한 음성의 특징 벡터 변환방법을 제안한다. 제안한 방법은 여러 환경에서 수집된 음성신호의 켑스트럼 벡터를 다수의 특징 함수들의 선형결합으로 가정하고, 독립성분분석을 이용하여 분리된 켑스트럼 벡터를 학습과 인식에 사용한다. 변환된 벡터 영역에서는 반복적으로 나타나는 화자의 특징 정보는 강조되고 임의로 나타나는 채널 왜곡은 억제되는 효과를 볼 수 있다. 제안된 방법의 유효성을 검증하기 위해 실제 전화음성으로 문장독립형 화자식별 실험을 수행하였으며, 결과를 통해 독립성분분석을 이용한 특징벡터의 변환이 채널 환경 변화에 대해 보다 강인함을 보였다.

• 음성과학
• /
• 제7권2호
• /
• pp.235-244
• /
• 2000

This paper was focused on realizing the text-independent speaker recognizer using the VQ and GMM algorithm and studying the characteristics of the speaker recognizers that adopt these two algorithms. Because it was difficult ascertain the effect two algorithms have on the speaker recognizer theoretically, we performed the recognition experiments using various parameters and, as the result of the experiments, we could show that GMM algorithm had better recognition performance than VQ algorithm as following. The GMM showed better performance with small training data, and it also showed just a little difference of recognition rate as the kind of feature vectors and the length of input data vary. The GMM showed good recognition performance than the VQ on the whole.

• 한국통신학회논문지
• /
• 제25권3B호
• /
• pp.565-569
• /
• 2000

We compose the two-stage recurrent neural network that returns both signals of a hidden and an output layer to the hidden layer. It is tested on the basis of syllables for Korean spoken digit from /gong/to /gu. For these experiments, we adjust the neuron number of the hidden layer, the predictive order of input data and self-recurrent coefficient of the decision state layer. By the experimental results, the recognition rate of this neural network is between 91% and 97.5% in the speaker-dependent case and between 80.75% and 92% in the speaker-independent case. In the speaker-dependent case, this network shows an equivalent recognition performance to Jordan and Elman network but in the speaker-independent case, it does improved performance.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.123-126
• /
• 2003

We discuss how to reduce the number of inverse matrix and its dimensions requested in MLLR framework for speaker adaptation. To find a smaller set of variables with less redundancy, we employ PCA(principal component analysis) and ICA(independent component analysis) that would give as good a representation as possible. The amount of additional computation when PCA or ICA is applied is as small as it can be disregarded. The dimension of HMM parameters is reduced to about 1/3 ~ 2/7 dimensions of SI(speaker independent) model parameter with which speech recognition system represents word recognition rate as much as ordinary MLLR framework. If dimension of SI model parameter is n, the amount of computation of inverse matrix in MLLR is proportioned to O($n^4$). So, compared with ordinary MLLR, the amount of total computation requested in speaker adaptation is reduced to about 1/80~1/150.

• 대한음성학회지:말소리
• /
• 제56호
• /
• pp.147-158
• /
• 2005

In this paper, we are focused to develop the simplified speaker verification algorithm without background speaker models, which will be adopted in the portable speaker verification system equipped in portable terminals such as mobile phone and PMP. According to the tolerance interval analysis, the population of someone's speaker model can be represented by a suitable number of selected independent samples of speaker model. So we can make the representative speaker model and threshold under the specified confidence level and coverage. Using proposed algorithm with the number of samples is 40, the experiments show that the false rejection rate is $3.0\%$ and the false acceptance rate $4.3\%$, worth comparing to conventional method's results, $5.4\%\;and\;5.5\%$, respectively. Next step of research will be on the suitable adaptation methods to overcome speech variation problems due to aging effect and operating environments.

• 음성과학
• /
• 제12권4호
• /
• pp.31-42
• /
• 2005

Recently, Gaussian Mixture Model (GMM), a special form of CHMM, has been applied to speaker identification and it has proved that performance of GMM is better than CHMM. Therefore, in this paper the speaker models based on GMM and a new GMM using the modified EM algorithm are introduced and evaluated for text-independent speaker identification. Various experiments were performed to evaluate identification performance of two algorithms. As a result of the experiments, the GMM speaker model attained 94.6% identification accuracy using 40 seconds of training data and 32 mixtures and 97.8% accuracy using 80 seconds of training data and 64 mixtures. On the other hand, the new GMM speaker model achieved 95.0% identification accuracy using 40 seconds of training data and 32 mixtures and 98.2% accuracy using 80 seconds of training data and 64 mixtures. It shows that the new GMM speaker identification performance is better than the GMM speaker identification performance.

• 대한음성학회지:말소리
• /
• 제54호
• /
• pp.73-83
• /
• 2005

The goal of our research is to build a text-independent speaker identification system that can be used in any condition without any additional adaptation process. The performance of speaker recognition systems can be severely degraded in some unknown mismatched microphone and noise conditions. In this paper, we show that PCA(principal component analysis) can improve the performance in the situation. We also propose an augmented PCA process, which augments class discriminative information to the original feature vectors before PCA transformation and selects the best direction for each pair of highly confusable speakers. The proposed method reduced the relative recognition error by 21%.

• 로봇학회논문지
• /
• 제1권2호
• /
• pp.158-162
• /
• 2006

This paper presents a speaker recognition system intended for use in human-robot interaction. The proposed speaker recognition system can achieve significantly high performance in the Ubiquitous Robot Companion (URC) environment. The URC concept is a scenario in which a robot is connected to a server through a broadband connection allowing functions to be performed on the server side, thereby minimizing the stand-alone function significantly and reducing the robot client cost. Instead of giving a robot (client) on-board cognitive capabilities, the sensing and processing work are outsourced to a central computer (server) connected to the high-speed Internet, with only the moving capability provided by the robot. Our aim is to enhance human-robot interaction by increasing the performance of speaker recognition with multiple microphones on the robot side in adverse distant-talking environments. Our speaker recognizer provides the URC project with a basic interface for human-robot interaction.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.159-162
• /
• 2005

Identification is the process automatically identify who is speaking on the basis of information obtained from speech waves. In training phase, each speaker models are trained using each speaker's speech data. GMMs (Gaussian Mixture Models), which have been successfully applied to speaker modeling in text-independent speaker identification, are not efficient in insufficient training data environment. This paper proposes speaker modeling method using MLLR (Maximum Likelihood Linear Regression) method which is used for speaker adaptation in speech recognition. We make SD-like model using MLLR adaptation method instead of speaker dependent model (SD). Proposed system outperforms the GMMs in small training data environment.

• 한국정보통신학회논문지
• /
• 제8권2호
• /
• pp.359-364
• /
• 2004

본 논문에서는 범용 디지털 신호처리기를 이용한 잡음환경에 강인한 실시간 화자 독립 음성인식 시스템을 구현하였다. 구현된 시스템은 TI사의 범용 부동소수점 디지털 신호처리기인 TMS320C32를 이용하였고, 실시간 음성 입력을 위한 음성 CODEC과 외부 인터페이스를 확장하여 인식결과를 출력하도록 구성하였다. 실시간 음성 인식기에 사용한 음성특징 파라메터는 일반적으로 사용되어 지는 MFCC(Mel Frequency Cepstral Coefficient)대신 독립성분분석을 통해 MFCC의 특징 공간을 변화시킨 파라메터를 사용하여 외부잡음 환경에 강인한 특성을 지니도록 하였다. 두 가지 특징 파라메터에 대해 잡음 환경에서의 인식실험 결과, 독립성분 분석에 의한 특징 파라메터의 인식 성능이 MFCC보다 우수함을 확인 할 수 있었다.