• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 전문대학교육위원
• /
• pp.176-179
• /
• 2005

In this paper, we propose the new method that separate the existing common VQ code book into two parts, one is the common VQ code book which is the half of existing common VQ code book, another is the personal speaker VQ code book which accommodate the personal speaker characteristic, variation to improve the performance of the text-dependent speaker verification system using discrete HMM. We apply the propose method m this paper to the text-dependent speaker verification system using discrete HMM and have the improvement performance of about 0.24% compared to existing method

• 음성과학
• /
• 제2권
• /
• pp.57-66
• /
• 1997

This paper studies the effects of the method, CMS(Cepstral Mean Subtraction), (which compensates for some of the speech distortion. caused by telephone channels), on the performance of the text-dependent speaker identification system. This system is based on the VQ(Vector Quantization) and HMM(Hidden Markov Model) method and chooses the LPC-Cepstrum and Mel-Cepstrum as the feature vectors extracted from the speech data transmitted through telephone channels. Accordingly, we can compare the correct recognition rates of the speaker identification system between the use of LPC-Cepstrum and Mel-Cepstrum. Finally, from the experiment results table, it is found that the Mel-Cepstrum parameter is proven to be superior to the LPC-Cepstrum and that recognition performance improves by about 10% when compensating for telephone channel using the CMS.

• 제어로봇시스템학회논문지
• /
• 제16권4호
• /
• pp.335-338
• /
• 2010

A new method that improves the performance of large scale voice dialling system is presented using speaker adaptation. Since SI (Speaker Independent) based speech recognition system with phoneme HMM uses only the phoneme string of the input sentence, the storage space could be reduced greatly. However, the performance of the system is worse than that of the speaker dependent system due to the mismatch between the input utterance and the SI models. A new method that estimates the phonetic string and adaptation vectors iteratively is presented to reduce the mismatch between the training utterances and a set of SI models using speaker adaptation techniques. For speaker adaptation the stochastic matching methods are used to estimate the adaptation vectors. The experiments performed over actual telephone line shows that proposed method shows better performance as compared to the conventional method. with the SI phonetic recognizer.

• IEIE Transactions on Smart Processing and Computing
• /
• 제2권5호
• /
• pp.277-281
• /
• 2013

Modern speaker verification systems based on support vector machines (SVMs) use Gaussian mixture model (GMM) supervectors as their input feature vectors, and the maximum a posteriori (MAP) adaptation is a conventional method for generating speaker-dependent GMMs by adapting a universal background model (UBM). MAP adaptation requires the appropriate amount of input utterance due to the number of model parameters to be estimated. On the other hand, with limited utterances, unreliable MAP adaptation can be performed, which causes adaptation noise even though the Bayesian priors used in the MAP adaptation smooth the movements between the UBM and speaker dependent GMMs. This paper proposes a sparse MAP adaptation method, which is known to perform well in the automatic speech recognition area. By introducing sparse MAP adaptation to the GMM-SVM-based speaker verification system, the adaptation noise can be mitigated effectively. The proposed method utilizes the L0 norm as a regularizer to induce sparsity. The experimental results on the TIMIT database showed that the sparse MAP-based GMM-SVM speaker verification system yields a 42.6% relative reduction in the equal error rate with few additional computations.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.409-412
• /
• 2002

There is a growing interest in speaker verification, which verifies someone by his/her voices. This paper explains the traditional text-dependent speaker verification algorithms, DTW and HMM. This paper also introduces SVM and how this can be applied to speaker verification system. Experiments were conducted with Korean database using these algorithms. The results of experiments indicated SVM is superior to other algorithms. The EER of SVM is only 0.5% while that of HMM is 5.4%.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 춘계학술대회 학술발표 논문집 제14권 제1호
• /
• pp.515-518
• /
• 2004

This paper presents a method that improves the performance of the personal voice dialling system in which speaker Independent phoneme HMM's are used. Since the speaker independent phoneme HMM based voice dialing system uses only the phone transcription of the input sentence, the storage space could be reduced greatly. However, the performance of the system is worse than that of the system which uses the speaker dependent models due to the phone recognition errors generated when the speaker Independent models are used. In order to solve this problem, a new method that jointly estimates transformation vectors for the speaker adaptation and transcriptions from training utterances is presented. The biases and transcriptions are estimated iteratively from the training data of each user with maximum likelihood approach to the stochastic matching using speaker-independent phone models. Experimental result shows that the proposed method is superior to the conventional method which used transcriptions only.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.605-608
• /
• 2002

A text-dependent speaker recognition system using a robust matching process is studied. The feature histogram of LPC cepstral coefficients for matching is used. The matching process uses mixture network with penalty scores. Using probability and shape comparison of two feature histograms, similarity values are obtained. The experiment results will be shown to show the effectiveness of the proposed algorithm.

• ETRI Journal
• /
• 제40권5호
• /
• pp.643-652
• /
• 2018

Dysarthria is a degenerative disorder of the central nervous system that affects the control of articulation and pitch; therefore, it affects the uniqueness of sound produced by the speaker. Hence, dysarthric speaker recognition is a challenging task. In this paper, a feature-extraction method based on deep belief networks is presented for the task of identifying a speaker suffering from dysarthria. The effectiveness of the proposed method is demonstrated and compared with well-known Mel-frequency cepstral coefficient features. For classification purposes, the use of a multi-layer perceptron neural network is proposed with two structures. Our evaluations using the universal access speech database produced promising results and outperformed other baseline methods. In addition, speaker identification under both text-dependent and text-independent conditions are explored. The highest accuracy achieved using the proposed system is 97.3%.

• 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.

• 전자공학회논문지T
• /
• 제36T권2호
• /
• pp.56-62
• /
• 1999

본 논문은 음성으로 다이얼링하는 시스템으로써, 화자종속 한국어 숫자음을 인식을 하기 위한 하드웨어를 구성한 논문이다. 음성 다이얼링 시스템은 충격계수를 이용하여 한국어 숫자음을 인식하도록 하였다. 여기서 제안한 음성 다이얼링 시스템은 적분기, 레벨분별회로 그리고 인식프로그램으로 구성하였다. 아날로그 음성 신호는 차단 주파수 4.5(kHz)를 지닌 저주파 필터를 통해 음성 다이얼링 시스템에 입력하였다. 화자 종속 한국어 숫자음 인식은 하드웨어 시스템에 의해 확실하게 인식 되었음을 확인하였다. 실험결과는 한국어 숫자음 음성인식에 대해 평균 64(%)의 인식율이 나왔고, 숫자음 /사/, /오/, /육/, /칠/, /구/, /영/에 대해서는 100(%)의 인식율을 나타내었다.