A new nonlinear feature extraction algorithm for speaker verification
نویسندگان
چکیده
In this paper we propose a new feature extraction algorithm based on nonlinear prediction: the Neural Predictive Coding model which is an extension of the classical LPC one. This model is applied to speaker verification by the Arithmetic-Harmonic Sphericity (AHS) method. Two different initialization methods are proposed for the coding method based on the Neural Predictive Coding (NPC): classical neural networks initialization and linear initialization. The first model obtains smaller rates. For the linear initialization, we obtain significant improvement in comparison to the most used methods (LPCC, MFCC). This study opens a new way towards different feature extraction schemes that offers better accuracy on speaker recognition tasks.
منابع مشابه
Feature Extraction and Test Algorithm for Speaker Verification
In this paper we introduce two methods to improve text-independent speaker verification. In feature extraction process the feature vectors of voiced speech and unvoiced speech independently. In test process, the test speech is adapted to a new model instead of calculating the log-likelihood, then the Mahalanobis Distances among the UBM model, the speaker model and the test speech model are calc...
متن کاملSynthetic Speech Spoofing Detection using MFCC and SVM
Nowadays synthetic voice is frequently used to defraud a biometric access system which are speaker recognition based. This paper presents synthetic speech detection in automatic speaker verification system (ASV) for the purpose of spoof detection. Feature extraction is done by canonical Mel Frequency Cepstral Coefficients (MFCC) algorithm and classification of natural and synthetic voice are do...
متن کاملMulti Filter Bank Approach for Speaker Verification Based on Genetic Algorithm
Speech recognition systems usually need a feature extraction stage which aims at obtaining the best signal representation. State of the art speaker verification systems are based on cepstral features like MFCC, LFCC or LPCC. In this article, we propose a feature extraction system based on the combination of three feature extractors adapted to the speaker verification task. A genetic algorithm i...
متن کاملTime –Frequency Representation of Vocal Source Signal for Speaker Verification
We propose an effective feature extraction technique for obtaining essential time-frequency information from the linear prediction (LP) residual signal, which are closely related to the glottal vibration of individual speaker. With pitch synchronous analysis, wavelet transform is applied to every two pitch cycles of the LP residual signal to generate a new feature vector, called Wavelet Based F...
متن کاملتشخیص لهجه های زبان فارسی از روی سیگنال گفتار با استفاده از روش های استخراج ویژگی کارآمد و ترکیب طبقه بندها
Speech recognition has achieved great improvements recently. However, robustness is still one of the big problems, e.g. performance of recognition fluctuates sharply depending on the speaker, especially when the speaker has strong accent and difference Accents dramatically decrease the accuracy of an ASR system. In this paper we apply three new methods of feature extraction including Spectral C...
متن کامل