Isolated Word Recognition on an Embedded System
نویسندگان
چکیده
In this paper, an embedded isolated word recognition system, which is designed for command and control applications, is presented. The hardware is designed by using a 32 bit general purpose ARM7TDMI cored microcontroller and required peripherals. Vector Quantization (VQ) and Discrete Hidden Markov Model (HMM) based speech recognition algorithms are implemented on the embedded system. The system is tested on a data set containing fifty four Turkish words taken from forty speakers. Using this data set, the VQ classifier obtained 99% and HMM classifier obtained about 97% average recognition rates in simulations. Key-Words: Embedded systems, Isolated word recognition, Vector quantization, Hidden Markov models
منابع مشابه
Large vocabulary speaker independent isolated word recognition for embedded systems
In this paper the implementation of a word-stem based tree search for large vocabulary speaker independent isolated word recognition for embedded systems is presented. Two fast search algorithms combine the effectiveness of the tree structure for large vocabularies and the fast Viterbi search within the regular structures of word-stems. The algorithms are proved to be very effective for worksta...
متن کاملEvaluation of Features Extraction Algorithms for a Real-Time Isolated Word Recognition System
Paper presents an comparative evaluation of features extraction algorithm for a real-time isolated word recognition system based on FPGA. The Mel-frequency cepstral, linear frequency cepstral, linear predictive and their cepstral coefficients were implemented in hardware/software design. The proposed system was investigated in speaker dependent mode for 100 different Lithuanian words. The robus...
متن کاملAn embedded word training procedure for connected digit recognition
The "conventional" way of obtaining word reference patterns for connected word recognition systems is to use isolatàd word patterns, and to rely on the dynamics of the matching algorithm to account for the differences in connected speech. Connected word recognition, based on such an approach, tends to become unreliable (high error rates) when the talking rate becomes grossly incommensurate with...
متن کاملOn the Application of Embedded Digit Training to Speaker Independent Connected Digit Recognition
In recent years, several algorithms have been proposed for recognizing a string of connected words (typically digits) by optimally piecing together reference patterns corresponding to the words in the string. Although the algorithms differ greatly in details of implementation, storage requirements, etc., they all have essentially the same performance in that their ability to match the unknown s...
متن کاملA parallel multi-stream model for sign language recognition
In this paper, the sub-units in each stream are used and embedded in the multi-stream model. In this framework, sign language recognition system was implemented and evaluated. Experiments were carried out for 5177 Chinese signs. The real time isolated recognition rate is 95.1%. For continuous sign recognition, the word correct rate is 91.8%. This has shown that parallel multi-stream model is po...
متن کامل