• Title/Summary/Keyword: GMM

Search Result 535, Processing Time 0.032 seconds

Speaker Verification Using SVM Kernel with GMM-Supervector Based on the Mahalanobis Distance (Mahalanobis 거리측정 방법 기반의 GMM-Supervector SVM 커널을 이용한 화자인증 방법)

  • Kim, Hyoung-Gook;Shin, Dong
    • The Journal of the Acoustical Society of Korea
    • /
    • v.29 no.3
    • /
    • pp.216-221
    • /
    • 2010
  • In this paper, we propose speaker verification method using Support Vector Machine (SVM) kernel with Gaussian Mixture Model (GMM)-supervector based on the Mahalanobis distance. The proposed GMM-supervector SVM kernel method is combined GMM with SVM. The GMM-supervectors are generated by GMM parameters of speaker and other speaker utterances. A speaker verification threshold of GMM-supervectors is decided by SVM kernel based on Mahalanobis distance to improve speaker verification accuracy. The experimental results for text-independent speaker verification using 20 speakers demonstrates the performance of the proposed method compared to GMM, SVM, GMM-supervector SVM kernel based on Kullback-Leibler (KL) divergence, and GMM-supervector SVM kernel based on Bhattacharyya distance.

Performance Enhancement of Speaker Identification System Based on GMM Using the Modified EM Algorithm (수정된 EM알고리즘을 이용한 GMM 화자식별 시스템의 성능향상)

  • Kim, Seong-Jong;Chung, Ik-Joo
    • Speech Sciences
    • /
    • v.12 no.4
    • /
    • 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.

  • PDF

Speaker Identification using Phonetic GMM (음소별 GMM을 이용한 화자식별)

  • Kwon Sukbong;Kim Hoi-Rin
    • Proceedings of the KSPS conference
    • /
    • 2003.10a
    • /
    • pp.185-188
    • /
    • 2003
  • In this paper, we construct phonetic GMM for text-independent speaker identification system. The basic idea is to combine of the advantages of baseline GMM and HMM. GMM is more proper for text-independent speaker identification system. In text-dependent system, HMM do work better. Phonetic GMM represents more sophistgate text-dependent speaker model based on text-independent speaker model. In speaker identification system, phonetic GMM using HMM-based speaker-independent phoneme recognition results in better performance than baseline GMM. In addition to the method, N-best recognition algorithm used to decrease the computation complexity and to be applicable to new speakers.

  • PDF

Speech/Mixed Content Signal Classification Based on GMM Using MFCC (MFCC를 이용한 GMM 기반의 음성/혼합 신호 분류)

  • Kim, Ji-Eun;Lee, In-Sung
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • v.50 no.2
    • /
    • pp.185-192
    • /
    • 2013
  • In this paper, proposed to improve the performance of speech and mixed content signal classification using MFCC based on GMM probability model used for the MPEG USAC(Unified Speech and Audio Coding) standard. For effective pattern recognition, the Gaussian mixture model (GMM) probability model is used. For the optimal GMM parameter extraction, we use the expectation maximization (EM) algorithm. The proposed classification algorithm is divided into two significant parts. The first one extracts the optimal parameters for the GMM. The second distinguishes between speech and mixed content signals using MFCC feature parameters. The performance of the proposed classification algorithm shows better results compared to the conventionally implemented USAC scheme.

Improved Generalized Method of Moment Estimators to Estimate Diffusion Models (확산모형에 대한 일반화적률추정법의 개선)

  • Choi, Youngsoo;Lee, Yoon-Dong
    • The Korean Journal of Applied Statistics
    • /
    • v.26 no.5
    • /
    • pp.767-783
    • /
    • 2013
  • Generalized Method of Moment(GMM) is a popular estimation method to estimate model parameters in empirical financial studies. GMM is frequently applied to estimate diffusion models that are basic techniques of modern financial engineering. However, recent research showed that GMM had poor properties to estimate the parameters that pertain to the diffusion coefficient in diffusion models. This research corrects the weakness of GMM and suggests alternatives to improve the statistical properties of GMM estimators. In this study, a simulation method is adopted to compare estimation methods. Out of compared alternatives, NGMM-Y, a version of improved GMM that adopts the NLL idea of Shoji and Ozaki (1998), showed the best properties. Especially NGMM-Y estimator is superior to other versions of GMM estimators for the estimation of diffusion coefficient parameters.

Comparison Study on the Performances of NLL and GMM for Estimating Diffusion Processes (NLL과 GMM을 중심으로 한 확산모형 추정법 비교)

  • Kim, Dae-Gyun;Lee, Yoon-Dong
    • The Korean Journal of Applied Statistics
    • /
    • v.24 no.6
    • /
    • pp.1007-1020
    • /
    • 2011
  • Since the research of Black and Scholes (1973), modeling methods using diffusion processes have performed principal roles in financial engineering. In modern financial theories, various types of diffusion processes were suggested and applied in real situations. An estimation of the model parameters is an indispensible step to analyze financial data using diffusion process models. Many estimation methods were suggested and their properties were investigated. This paper reviews the statistical properties of the, Euler approximation method, New Local Linearization(NLL) method, and Generalized Methods of Moment(GMM) that are known as the most practical methods. From the simulation study, we found the NLL and Euler methods performed better than GMM. GMM is frequently used to estimate the parameters because of its simplicity; however this paper shows the performance of GMM is poorer than the Euler approximation method or the NLL method that are even simpler than GMM. This paper shows the performance of the GMM is extremely poor especially when the parameters in diffusion coefficient are to be estimated.

Speaker Identification Using GMM Based on Local Fuzzy PCA (국부 퍼지 클러스터링 PCA를 갖는 GMM을 이용한 화자 식별)

  • Lee, Ki-Yong
    • Speech Sciences
    • /
    • v.10 no.4
    • /
    • 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.

  • PDF

Research of Hybrid GMM/SVM Approach for Speaker Verification (화자 확인을 위한 하이브리드 GMM/SVM 방식에 대한 연구)

  • Yoon, You-Sun
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2008.05a
    • /
    • pp.139-140
    • /
    • 2008
  • 문장 독립 화자 확인에서 SVM을 위한 적응된 GMM을 바탕으로 특징을 추출함으로써 GMM과 SVM 사이의 새로운 접근 방식을 제안한다. 우수한 측정성으로 인해, 적응된 GMM은 SVM 화자 확인을 위한 대규모의 음성 데이터로부터 적은 양의, 전형적인 특징 벡터를 추출해오곤 했다. 이 새로운 접근방식을 사용함으로써, 제안된 화자 확인 시스템은 기존의 GMM-UBM 시스템보다 훨씬 나은 성능을 보였다.

Analysis and Implementation of Speech/Music Classification for 3GPP2 SMV Based on GMM (3GPP2 SMV의 실시간 음성/음악 분류 성능 향상을 위한 Gaussian Mixture Model의 적용)

  • Song, Ji-Hyun;Lee, Kye-Hwan;Chang, Joon-Hyuk
    • The Journal of the Acoustical Society of Korea
    • /
    • v.26 no.8
    • /
    • pp.390-396
    • /
    • 2007
  • In this letter, we propose a novel approach to improve the performance of speech/music classification for the selectable mode vocoder(SMV) of 3GPP2 using the Gaussian mixture model(GMM) which is based on the expectation-maximization(EM) algorithm. We first present an effective analysis of the features and the classification method adopted in the conventional SMV. And then feature vectors which are applied to the GMM are selected from relevant Parameters of the SMV for the efficient speech/music classification. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme of the SMV.

Scream Sound Detection Based on Universal Background Model Under Various Sound Environments (다양한 소리 환경에서 UBM 기반의 비명 소리 검출)

  • Chung, Yong-Joo
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.12 no.3
    • /
    • pp.485-492
    • /
    • 2017
  • GMM has been one of the most popular methods for scream sound detection. In the conventional GMM, the whole training data is divided into scream sound and non-scream sound, and the GMM is trained for each of them in the training process. Motivated by the idea that the process of scream sound detection is very similar to that of speaker recognition, the UBM which has been used quite successfully in speaker recognition, is proposed for use in scream sound detection in this study. We could find that UBM shows better performance than the traditional GMM from the experimental results.