Support vector machines using GMM supervectors for speaker verification

Campbell, William M.; Sturim, Douglas E.; Reynolds, Douglas A.

doi:10.1109/lsp.2006.870086

Cited by 898 publications

(497 citation statements)

References 8 publications

Supporting

Mentioning

479

Contrasting

Unclassified

Order By: Relevance

“…To demonstrate the state-of-the-art acoustic speaker verification system can still be improved by high-level features, we also fused the scores obtained from AFCPMs and GMM-SVM [44]. For the GMM-SVM system, acoustic scores S GMM-SVM were computed based on the SVM framework [44]:…”

Section: Scoring Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A new adaptation approach to high-level speaker-model creation in speaker verification

Zhang

Mak

2009

Speech Communication

View full text Add to dashboard Cite

Research has shown that speaker verification based on high-level speaker features requires long enrollment utterances to guarantee low error rate during verification. However, in practical speaker verification, it is common to model speakers based on a limited amount of enrollment data, which will make the speaker models unreliable. This paper proposes four new adaptation methods for creating high-level speaker models to alleviate this undesirable effect. Unlike conventional methods in which only the phoneme-dependent background model is adapted, the proposed adaptation methods also adapts the phoneme-independent speaker model to fully utilize all the information available in the training data. A proportional factor, which is derived from the ratio between the phoneme-dependent background model and the phoneme-independent background model, is used to adjust the phonemeindependent speaker models during adaptation. The proposed method was evaluated under the NIST 2000 and NIST 2002 SRE frameworks. Experimental results show that the proposed adaptation method can alleviate the data-sparseness problem effectively and achieves a better performance when compared with traditional MAP adaptation.

show abstract

Section: Scoring Methodsmentioning

confidence: 99%

“…is the GMM-supervector kernel [44]. λ i and Σ i are the mixture weights and covariances of UBM Gaussians, respectively.…”

Section: Scoring Methodsmentioning

confidence: 99%

A new adaptation approach to high-level speaker-model creation in speaker verification

Zhang

Mak

2009

Speech Communication

View full text Add to dashboard Cite

show abstract

“…기존의 GMM-UBM [11] 에 기반한 SV 방법 [12] 은 음 악 신호에서 얻어지는 특징들을 모아서 차수가 크긴 하지만 하나의 벡터로 만들어 줌으로써 검색에 쉽게 활용할 수 있는 장점이 있어 큰 관심을 받아왔다. [8,9] 최근 SV 계산 시에 GMM의 계산량을 줄일 수 있는 k-means 군집화를 대신 이용하는 무게중심 모델에 기반한 음악 검색 방법이 제안되었다.…”

Section: 알파 다이버전스를 이용한 무게중심 모델 기반 음악 유사도unclassified

Centroid-model based music similarity with alpha divergence

Seo¹,

Kim²,

Park³

2016

The Journal of the Acoustical Society of Korea

View full text Add to dashboard Cite

Music-similarity computation is crucial in developing music information retrieval systems for browsing and classification. This paper overviews the recently-proposed centroid-model based music retrieval method and applies the distributional similarity measures to the model for retrieval-performance evaluation. Probabilistic distance measures (also called divergence) compute the distance between two probability distributions in a certain sense. In this paper, we consider the alpha divergence in computing distance between two centroid models for music retrieval. The alpha divergence includes the widely-used Kullback-Leibler divergence and Bhattacharyya distance depending on the values of alpha. Experiments were conducted on both genre and singer datasets. We compare the music-retrieval performance of the distributional similarity with that of the vector distances. The experimental results show that the alpha divergence improves the performance of the centroid-model based music retrieval.

show abstract

“…In order to be able to classify recordings using SVM each recording is transformed to the one fixed-length vector. One method to do this is GMM supervector [5]. Where for each recording GMM model is trained and then each conversation is represented by the vector that is concatenation of means of GMM model.…”

Section: Multi-level Speaker Recognitionmentioning

confidence: 99%

Speaker recognition based on multilevel speech signal analysis on Polish corpus

Drgas

Dąbrowski

2013

Multimed Tools Appl

View full text Add to dashboard Cite

This article deals with a new approach to the text-independent speaker verification task. It is namely proposed to combine spectral and the so-called highlevel features (prosodic, articulatory, and lexical) in order to increase accuracy of speaker verification. The presented experiments were performed using a Polish language corpus developed by the authors, the so-called PUEPS corpus. It contains semi-spontaneous telephone conversations (acted emergency telephone notifications) recorded in laboratory conditions. As the Polish language is under resourced and the PUEPS corpus is relatively small, in this case a new approach is needed, other than these well known from NIST (National Institute of Standards and Technology) evaluations. The authors proposed to use the fast scoring instead of more complex classifiers and the AdaBoost (adaptive boosting) algorithm for features combination. Combination of features resulted in the equal error rate (EER) reduction for various SNR (signal-to-noise ratio) conditions. Additionally, score normalization methods were evaluated. It was shown that significant benefits can be obtained using the z-norm2 method.

show abstract

Support vector machines using GMM supervectors for speaker verification

Cited by 898 publications

References 8 publications

A new adaptation approach to high-level speaker-model creation in speaker verification

A new adaptation approach to high-level speaker-model creation in speaker verification

Centroid-model based music similarity with alpha divergence

Speaker recognition based on multilevel speech signal analysis on Polish corpus

Contact Info

Product

Resources

About