• 대한임베디드공학회논문지
• /
• 제10권2호
• /
• pp.65-71
• /
• 2015

It has been known that GMM (Gaussian Mixture Model) based speaker identification systems using ML (Maximum Likelihood) and WMR (Weighting Model Rank) demonstrate very high performances. However, such systems are not so effective under practical environments, in terms of real time processing, because of their high calculation costs. In this paper, we propose a new speaker-pruning algorithm that effectively reduces the calculation cost. In this algorithm, we select 20% of speaker models having higher likelihood with a part of input speech and apply MWMR (Modified Weighted Model Rank) to these selected speaker models to find out identified speaker. To verify the effectiveness of the proposed algorithm, we performed speaker identification experiments using TIMIT database. The proposed method shows more than 60% improvement of reduced processing time than the conventional GMM based system with no pruning, while maintaining the recognition accuracy.

• 대한음성학회지:말소리
• /
• 제61호
• /
• pp.113-123
• /
• 2007

The environmental differences between training and testing mode are generally considered to be the critical factor for the performance degradation in speaker recognition systems. Especially, general speaker recognition systems try to get as clean speech as possible to train the speaker model, but it's not true in real testing phase due to environmental and channel noise. So in this paper, the new method of weighting the frame-based likelihood according to frame SNR is proposed in order to cope with that problem. That is to make use of the deep correlation between speech SNR and speaker discrimination rate. To verify the usefulness of this proposed method, it is applied to the context dependent speaker identification system. And the experimental results with the cellular phone speech DB which is designed by ETRI for Koran speaker recognition show that the proposed method is effective and increase the identification accuracy by 11% at maximum.

• 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.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권1호
• /
• pp.76-82
• /
• 2005

Speech signal has various features of speakers. This feature is extracted from speech signal processing. The speaker is identified by the speaker identification system. In this paper, we propose the speaker identification system that uses the incremental learning based on neural network. Recorded speech signal through the microphone is blocked to the frame of 1024 speech samples. Energy is divided speech signal to voiced signal and unvoiced signal. The extracted 12 orders LPC cpestrum coefficients are used with input data for neural network. The speakers are identified with the speaker identification system using the neural network. The neural network has the structure of MLP which consists of 12 input nodes, 8 hidden nodes, and 4 output nodes. The number of output node means the identified speakers. The first output node is excited to the first speaker. Incremental learning begins when the new speaker is identified. Incremental learning is the learning algorithm that already learned weights are remembered and only the new weights that are created as adding new speaker are trained. It is learning algorithm that overcomes the fault of neural network. The neural network repeats the learning when the new speaker is entered to it. The architecture of neural network is extended with the number of speakers. Therefore, this system can learn without the restricted number of speakers.

• International Journal of Computer Science & Network Security
• /
• 제24권10호
• /
• pp.43-52
• /
• 2024

A medium scale Urdu speakers' and English speakers' database with multiple accents and dialects has been developed to use in Urdu Speaker Verification Systems, English Speaker Verification Systems, accents and dialect verification systems. Urdu is the national language of Pakistan and English is the official language. Majority of the people are non-native Urdu speakers and non-native English in all regions of Pakistan in general and Gilgit-Baltistan region in particular. In order to design Urdu and English speaker verification systems for security applications in general and telephone banking in particular, two databases has been designed one for foreign accent of Urdu and another for foreign accent of English language. For the design of databases, voice data is collected from 180 speakers from GB region of Pakistan who could speak Urdu as well as English. The speakers include both genders (males and females) with different age groups ranging from 18 to 69 years. Finally, using a subset of the data, Multilayer Perceptron based speaker verification system has been designed. The designed system achieved overall accuracy rate of 83.4091% for English dataset and 80.0454% for Urdu dataset. It shows slight differences (4.0% with English and 7.4% with Urdu) in recognition accuracy if compared with the recently proposed multilayer perceptron (MLP) based SIS achieved 87.5% recognition accuracy

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1042-1045
• /
• 2003

In this paper, we propose the speaker identification system that uses vowel that has speaker's characteristic. System is divided to speech feature extraction part and speaker identification part. Speech feature extraction part extracts speaker's feature. Voiced speech has the characteristic that divides speakers. For vowel extraction, formants are used in voiced speech through frequency analysis. Vowel-a that different formants is extracted in text. Pitch, formant, intensity, log area ratio, LP coefficients, cepstral coefficients are used by method to draw characteristic. The cpestral coefficients that show the best performance in speaker identification among several methods are used. Speaker identification part distinguishes speaker using Neural Network. 12 order cepstral coefficients are used learning input data. Neural Network's structure is MLP and learning algorithm is BP (Backpropagation). Hidden nodes and output nodes are incremented. The nodes in the incremental learning neural network are interconnected via weighted links and each node in a layer is generally connected to each node in the succeeding layer leaving the output node to provide output for the network. Though the vowel extract and incremental learning, the proposed system uses low learning data and reduces learning time and improves identification rate.

• The Journal of the Acoustical Society of Korea
• /
• 제26권3E호
• /
• pp.80-86
• /
• 2007

In this paper, we utilize generalized warped filterbanks to improve the performance of speaker recognition systems. At first, the performance of speaker identification systems is analyzed by varying the type of warped filterbanks. Based on the results that the error pattern of recognition system is different depending on the type of filterbank used, we combine the likelihood values of the statistical models that consist of the features extracting from multiple warped filterbanks. Simulation results with TIMIT and NTIMIT database verify that the proposed system shows relative improvement of identification rate by 31.47% and 15.14% comparing it to the conventional system.

• 한국지능시스템학회논문지
• /
• 제8권2호
• /
• pp.82-95
• /
• 1998

본 논문에서는 구문독립 화지인식 시스템에서 가장 중요한 역할을 하는 분류기를 두 단계로 나누어, 먼저 짧은 구간들에 대해서 각각의 화자에 속하는 정도를 계산하고, 다음에 계산된 결과들을 가지고 주어진 음성구간전체에 대해 가장 가능성이 높은 화자를 선택하는 구조를 제안한다. 첫번째 부분은 학습에 의해 스스로 조기하는 RBFN을 이용하여 구현하고 두번째 부분에서는 MAXNET과 지연합의 조합으로 화자를 결정한다. 이렇게 함으로써 지연합의 개수가 증가함에 따라 인식률이 100%가 되는 것을 모의 실험을 통하여 확인한다. 또한 본 논문에서는 음성의 프랙탈적인 특징이 화자인식에 사용될 수 있는지를 검토한다. 화자인식은 동질의 집단에서 13명의 성인만자의 목소리를 이용하여 닫힌집합(closed-set)의 경우로 모의실험을 하였고, 기존의 특징으로는 선형예측계수(LPC) 와 PC-cepstrum을 사용하였다.

• 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.

• 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%.