Robust speaker identification based on selective use of feature vectors
نویسندگان
چکیده
A new method for speaker identification that selectively uses feature vectors for robust decision-making is described. Experimental results, with short speech segments ranging from 0.25 to 2 s, showed that our method consistently outperforms other approaches yielding relative improvements of 20–51% and 15–30% over baseline GMM and the LDA-GMM systems, respectively. 2006 Elsevier B.V. All rights reserved.
منابع مشابه
Feature vector classification by threshold for speaker identification
This paper describes a new feature vector classification method for speaker identification. Purpose of this paper is constructing robust speaker models which only use meaningful feature vectors and discard confusing feature vectors. To construct robust speaker model, proposed method classifies feature vectors using log-likelihood estimation. Experimental results, with various segments ranging f...
متن کاملGmm Based on Local Robust Pca for Speaker Identification
ABSTRACT: To solve the problems of outliers and high dimensionality of training feature vectors in speaker identification, in this paper, we propose an efficient GMM based on local robust PCA with VQ. The proposed method firstly partitions the data space into several disjoint regions by VQ, and then performs robust PCA using the iteratively reweighted covariance matrix in each region. Finally, ...
متن کاملNew distance measures for text-independent speaker identification
Distance measures [1][2][3] based on the covariance matrix of feature vectors were applied to text-independent speaker verification and identification. However, some of them do not satisfy the symmetric property which is fundamental to a distance measure. In this paper, we propose several symmetric distance measures based on the covariance matrix of feature vectors, and then construct some adva...
متن کاملSpeaker-independent emotion recognition based on feature vector classification
This paper proposes a new feature vector classification for speech emotion recognition. The conventional feature vector classification applied to speaker identification categorized feature vectors as overlapped and non-overlapped. This method discards all of the overlapped vectors in model training, while non-overlapped vectors are used to reconstruct corresponding speaker models. Although the ...
متن کاملOptimal fusion of diverse feature sets for speaker identification: an alternative method
For speaker identification, a robust and effective feature extraction method is necessary. But in the current circumstance, there exists no perfect feature that could optimally characterize physiological difference among speakers regardless of personal variation. A soft competition scheme for optimal fusion of diverse feature sets is applied to speaker identification in order to achieve the imp...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Pattern Recognition Letters
دوره 28 شماره
صفحات -
تاریخ انتشار 2007