Text-Independent Speaker Verification: The WCL-1 System
نویسندگان
چکیده
A text-independent Probabilistic Neural Network (PNN)-based speaker verification system, referred to as WCL-1, is presented. A modular structure, with a distinct PNN for each enrolled speaker, is employed. A gender-dependent universal background model is created to represent the world of possible impostor speakers. Beside portrayal of the WCL-1 system, a comprehensive description of the results obtained in the one-speaker detection task, during the 2002 NIST Speaker Recognition Evaluation is presented.
منابع مشابه
The WCL-1 System in the NIST Year 2004 Speaker Recognition Evaluation
Our text-independent speaker verification system, referred to as WCL-1, is based on Probabilistic Neural Networks (PNNs). WCL-1 has a modular structure with a distinct PNN for each enrolled user. A gender-dependent reference model, representing the world of possible impostors, is employed for counterbalancing the scores produced by the users’ models. The year 2004 WCL-1 system is basically a re...
متن کاملOne-Speaker Detection – Limited Data: The WCL-1 System
Our text-independent Probabilistic Neural Network (PNN)-based speaker verification system, referred to as WCL-1, a participant in the One-Speaker Detection Task of the 2003 NIST Speaker Recognition Evaluation (SRE), is presented here. The WCL-1 system is built on modular structure with a distinct PNN for each enrolled user. A gender-dependent universal background model, representing the world o...
متن کاملToward 2003 NIST Speaker Recognition Evaluation : The WCL - 1 System
A detailed description of our text-independent speaker verification (SV) system, referred to as WCL-1, a participant in the one-speaker detection task of the 2003 NIST Speaker Recognition Evaluation (SRE) is presented. It is an improved version of our baseline system, which has successfully participated in the 2002 NIST SRE. In addition to the short-term spectrum represented by the Mel-frequenc...
متن کاملThe WCL-1 System in the 2003 NIST Speaker Recognition Evaluation and 2003 NFI/TNO Forensic Speaker Recognition Evaluation
In the present work we discuss the results, which our speaker verification system, WCL-1, obtained in the 2003 NFI/TNO Forensic Speaker Recognition Evaluation. These results, together with the ones obtained in the 2003 NIST Speaker Recognition Evaluation, give opportunity for in depth analysis of the various aspects of real-world application of the speaker recognition technology. Based on the d...
متن کاملBenchmarking Feature Selection Techniques on the Speaker Verification Task
As a part of our preparation for the 2004 NIST Speaker Recognition Evaluation, we evaluated the practical usefulness of five feature ranking and selection methods. Seeking for improvement of the overall performance of our speaker verification system, WCL-1, we studied the relevance and contribution of the individual speech parameters. Furthermore, the choice of an appropriate dimensionality of ...
متن کامل