Effectiveness of LP Based Features for Identification of Professional Mimics in Indian Languages
نویسندگان
چکیده
Automatic Speaker Recognition (ASR) is an economic tool for voice biometrics because of availability of low cost and powerful processors. For an ASR system to be successful in practical environments, it must have high mimic resistance, i.e., the system should not be defeated by determined mimics which may be either identical twins or professional mimics. In this paper, we demonstrate the effectiveness of Linear Prediction (LP) based features viz. Linear Prediction Coefficients (LPC) and Linear Prediction Cepstral Coefficients (LPCC) over filterbank based features such as Mel-Frequency Cepstral Coefficients (MFCC) and newly proposed Teager energy based MFCC (T-MFCC) for the identification of professional mimics in Marathi and Hindi languages.
منابع مشابه
Growth of Green Marketing –A Literature perspective of Green Indian Economy
Green Marketing is becoming a buzz for the society nowadays and people start shifting their demands towards a product which is related towards environmental safeguard. Nowadays companies from different industries sectors are showing their keen interest and taking various initiatives towards green marking. Electronic products having eco safeguard and are less detrimental to the environment are l...
متن کاملمقایسه روش های طیفی برای شناسایی زبان گفتاری
Identifying spoken language automatically is to identify a language from the speech signal. Language identification systems can be divided into two categories, spectral-based methods and phonetic-based methods. In the former, short-time characteristics of speech spectrum are extracted as a multi-dimensional vector. The statistical model of these features is then obtained for each language. The ...
متن کاملIdentification of effectiveness assessment criteria for Seminary virtual courses
The main purpose of this research is to derive Seminary virtual education effectiveness criteria. Seminary education has main differences with tertiary or professional education. Therefore, to assess their effectiveness, we must take into account these differences. In this research we have used qualitative methodology and set a semi-interview mechanism with 15 experts in e-learning, all employe...
متن کاملAutoassociative Neural Network Models for Language
The objective of this paper is t o demonstrate the feasibility of automatic language identification (LID) systems, using spectral features. T h e powerful features of autoassociative neural network models are exploited for capturing the language specific features for developing the language identification system. The nonlinear models capture the complex distribution of spectral vectors in the f...
متن کاملOn minimal realization of IF-languages: A categorical approach
he purpose of this work is to introduce and study the concept of minimal deterministic automaton with IF-outputs which realizes the given IF-language. Among two methods for construction of such automaton presented here, one is based on Myhill-Nerode's theory while the other is based on derivatives of the given IF-language. Meanwhile, the categories of deterministic automata with IF-outputs and ...
متن کامل