Study on Text-Dependent Speaker Recognition Based on Biomimetic Pattern Recognition
نویسندگان
چکیده
We studied the application of Biomimetic Pattern Recognition to speaker recognition. A speaker recognition neural network using network matching degree as criterion is proposed. It has been used in the system of textdependent speaker recognition. Experimental results show that good effect could be obtained even with lesser samples. Furthermore, the misrecognition caused by untrained speakers occurring in testing could be controlled effectively. In addition, the basic idea “cognition” of Biomimetic Pattern Recognition results in no requirement of retraining the old system for enrolling new speakers.
منابع مشابه
Study on Closed-set Speaker Identification Based on Biomimetic Pattern Recognition
— In this PaPer.a new classifier of speaker identification has been proposed, which is based on Biomimetic pattern recognition (BPR). Distinguished from traditional speaker rec0gnition m ethods, such as DW T.HM M ,G M M .SV M and so on,the proposed clas— sifier is constructed by som e finite sub-space which is reasonable covering of the points in high dim ensional space according to distributin...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملBiomimetic Pattern Recognition
In speaker-independent speech recognition, the disadvantage of the most diffused technology ( Hidden Markov Models) is not only the need of many more training samples, but also long train time requirement. This paper describes the use of Biomimetic Pattern Recognition (BPR) in recognizing some Mandarin Speech in a speaker-independent manner. The vocabulary of the system consists of 15 Chinese d...
متن کاملVery Low Rate Speech Coding Algorithm Based on Biomimetic Pattern Recognition ⋆
Based on the speech coding technology, in this paper we propose a new method encoding the speech signal by the bionic pattern recognition technique. Using this new encoding method, the text message can be received after using biomimetic pattern recognition of the speaker’s voice. And the information related to the speaker’s individual characteristics can be obtained by “comparison” between the ...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کامل