Decision trees with improved efficiency for fast speaker verification
نویسندگان
چکیده
Classification and regression trees (CART) are convenient for low complexity speaker recognition on embedded devices. However, former attempts at using trees performed quite poorly compared to state of the art results with Gaussian Mixture Models (GMM). In this article, we introduce some solutions to improve the efficiency of the tree-based approach. First, we propose to use at the tree construction level different types of information from the GMM used in state of the art techniques. Then, we model the score function within each leaf of the tree by a linear score function. Considering a baseline state of the art system with an equal error rate (EER) of 8.6% on the NIST 2003 evaluation, a previous CART method provides typical EER ranging between 16% and 18% while the proposed improvements decrease the EER to 11.5%, with a computational cost suitable for embedded devices.
منابع مشابه
Title Speaker Recognition Using Adaptively Boosted Decision Tree Classifier( Accepted Version )
In this paper, a novel approach for speaker recognition is proposed. The approach makes use of adaptive boosting (AdaBoost) and C4.5 decision trees for closed set, text-dependent speaker recognition. A subset of 20 speakers, 10 male and 10 female, drawn from the YOHO speaker verification corpus is used to assess the performance of the system. Results reveal that an accuracy of 99.5% of speaker ...
متن کاملProbabilistic scoring using decision trees for fast and scalable speaker recognition
In the context of fast and low cost speaker recognition, this article investigates several techniques based on decision trees. A new approach is introduced where the trees are used to estimate a score function rather than returning a decision among classes. This technique is developed to approximate the GMM log-likelihood ratio (LLR) score function. On top of this approach, different solutions ...
متن کاملUsing Exciting and Spectral Envelope Information and Matrix Quantization for Improvement of the Speaker Verification Systems
Speaker verification from talking a few words of sentences has many applications. Many methods as DTW, HMM, VQ and MQ can be used for speaker verification. We applied MQ for its precise, reliable and robust performance with computational simplicity. We also used pitch frequency and log gain contour for further improvement of the system performance.
متن کاملText dependent speaker verification using binary classifiers
This paper describes how a speaker verification task can be advantageously decomposed into a series of binary classification problems, i.e. each problem discriminating between two classes only. Each binary classifier is specific to one speaker, one anti-speaker and one word. Decision trees dealing with attributes of continuous values are used as classifiers. The set of classifiers is then prune...
متن کاملUsing Exciting and Spectral Envelope Information and Matrix Quantization for Improvement of the Speaker Verification Systems
Speaker verification from talking a few words of sentences has many applications. Many methods as DTW, HMM, VQ and MQ can be used for speaker verification. We applied MQ for its precise, reliable and robust performance with computational simplicity. We also used pitch frequency and log gain contour for further improvement of the system performance.
متن کامل