• 음성과학
• /
• 제9권2호
• /
• pp.135-146
• /
• 2002

Generally a speaker verification system improves its system recognition ratio by regularizing log likelihood ratio, using a speaker model and its background speaker model that are required to be verified. The speaker-based cohort method is one of the methods that are widely used for selecting background speaker model. Recently, Gaussian-based cohort model has been suggested as a virtually synthesized cohort model, and unlike a speaker-based model, this is the method that chooses only the probability distributions close to basic speaker's probability distribution among the several neighboring speakers' probability distributions and thereby synthesizes a new virtual speaker model. It shows more excellent results than the existing speaker-based method. This study compared the existing speaker-based background speaker models and virtual speaker models and then constructed new virtual background speaker model groups which combined them in a certain ratio. For this, this study constructed a speaker verification system that uses GMM (Gaussin Mixture Model), and found that the suggested method of selecting virtual background speaker model shows more improved performance.

• 음성과학
• /
• 제7권1호
• /
• pp.31-37
• /
• 2000

This paper concerns effective speaker adaptation methods to solve the over-training problem in speaker verification, which frequently occurs when modeling a speaker with sparse training data. While various speaker adaptations have already been applied to speech recognition, these methods have not yet been formally considered in speaker verification. This paper proposes speaker adaptation methods using a combination of MAP and MLLR adaptations, which are successfully used in speech recognition, and applies to speaker verification. Experimental results show that the speaker verification system using a weighted MAP and MLLR adaptation outperforms that of the conventional speaker models without adaptation by a factor of up to 5 times. From these results, we show that the speaker adaptation method achieves significantly better performance even when only small training data is available for speaker verification.

• 음성과학
• /
• 제10권2호
• /
• pp.35-43
• /
• 2003

General speaker verification systems improve their recognition performances by normalizing log likelihood ratio, using a speaker model and its background speaker model that are required to be verified. So these systems rely heavily on the availability of much speaker independent databases for background speaker model design. This constraint, however, may be a burden in practical and portable devices such as palm-top computers or wireless handsets which place a premium on computations and memory. In this paper, new approach for the GMM-based background model design used in portable speaker verification system is presented when the enrollment data is available. This approach is to modify three parameters of GMM speaker model such as mixture weights, means and covariances along with reduced mixture order. According to the experiment on a 20 speaker population from YOHO database, we found that this method had a promise of effective use in a portable speaker verification system.

• 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.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 학술대회 논문집 정보 및 제어부문
• /
• pp.258-259
• /
• 2008

기존의 유선 연결을 이용한 Hometheater System은 점차 다채널로 발전하는Sound Format의 지원에 따라 복잡한 Speaker 연결 구조를 가지게 되어 오히려 사용자의 불편함을 만들고 이에 따라 일부 Speaker만을 사용하거나, 전면에 모든 Speaker를 배치하여 사용함에 따라 다채널 Speaker의 이점을 활용하지 못하고 있다. 이에 따라 점차 Wireless 기반의 다채널 Speaker에 대한 요구가 증가하고 있는데 현재 Wireless 기반의 각 Speaker Unit에 Data를 전송하는 과정에서 전송 delay가 발생하고 이 문제로 인해 Wireless Speaker의 보급에 빠르게 이루어지지 못하고 있는 상태에다. 이에 따라 본 논문에서는 무선랜을 이용한 무선 홈씨어터 시스템 구현에서 문제가 되는 전송Delay에 대해 보정 알고리즘을 통한 개선 방법을 제안한다.

• 전기학회논문지
• /
• 제66권7호
• /
• pp.1105-1110
• /
• 2017

Speech with various emotions degrades the performance of the speaker recognition system. In this paper, a speaker recognition method using emotional adaptation has been proposed to improve the performance of speaker recognition system using affective speech. For emotional adaptation, emotional speaker model was generated from speaker model without emotion using a small number of training affective speech and speaker adaptation method. Since it is not easy to obtain a sufficient affective speech for training from a speaker, it is very practical to use a small number of affective speeches in a real situation. The proposed method was evaluated using a Korean database containing four emotions. Experimental results show that the proposed method has better performance than conventional methods in speaker verification and speaker recognition.

• 문화기술의 융합
• /
• 제8권3호
• /
• pp.469-475
• /
• 2022

딥러닝 기반 1인 화자 TTS 시스템의 모델을 학습하기 위해서 수십 시간 분량의 음성 DB와 많은 학습 시간이 요구된다. 이것은 다화자 또는 개인화 TTS 모델을 학습시키기 위해서는 시간과 비용 측면에서 비효율적 방법이다. 음색 복제 방법은 새로운 화자의 TTS 모델을 생성하기 위하여 화자 인코더 모델을 이용하는 방식이다. 학습된 화자 인코더 모델을 통해 학습에 사용되지 않은 새로운 화자의 적은 음성 파일로부터 이 화자의 음색을 대표하는 화자 임베딩 벡터를 만든다. 본 논문에서는 음색 복제 방식을 적용한 다화자 TTS 시스템을 제안한다. 제안한 TTS 시스템은 화자 인코더, synthesizer와 보코더로 구성되어 있는데, 화자 인코더는 화자인식 분야에서 사용하는 d-vector 기법을 적용한다. 학습된 화자 인코더에서 도출한 d-vector를 synthesizer에 입력으로 추가하여 새로운 화자의 음색을 표현한다. MOS와 음색 유사도 청취 방법으로 도출한 실험 결과로부터 제안한 TTS 시스템의 성능이 우수함을 알 수 있다.

• 한국정보통신학회논문지
• /
• 제10권4호
• /
• pp.739-743
• /
• 2006

본 논문은 신경회로망을 이용한 화자적응 음성인식 제어시스템을 개발하였다. 화자종속시스템은 단일 화자의 음성만 등록하여 이용하므로 여러 화자의 음성을 인식하는 데는 문제가 있고, 화자독립시스템은 여러 화자를 인식한다. 본 연구 개발에서는 화자적응시스템을 구현하여 화자종속형의 단점을 보완하여 화자 독립과 화자 종속을 혼합하여 사용 할 수 있는 기능으로 화자 적용방법으로 구현하였고, 화자인증(Speaker Verification)도 가능하도록 프로그램 하였다.

• 음성과학
• /
• 제9권1호
• /
• pp.49-59
• /
• 2002

This paper concerns an effective text-dependent speaker verification method to increase the performance of speaker verification. While various speaker verification methods have already been developed, their effectiveness has not yet been formally proven in terms of achieving acceptable performance levels. This paper proposes a weighted likelihood procedure along with a confidence measure based on subword-based text-dependent speaker verification. Our aim is to remedy the low performance problem in speaker verification by exploring a means to strengthen the verification likelihood via subword-based hypothesis criteria and weighted likelihood method. Experimental results show that the proposed speaker verification method outperforms that of the speaker verification scheme without using the proposed decision by a factor of up to 1.6 times. From these results, the proposed speaker verification method is shown to be very effective and to achieve a reliable performance.

• 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.