Abstract
This article uses Field Programmable Gate Array (FPGA) as a carrier and uses IP core to form a System on Programmable Chip (SOPC) English speech recognition system. The SOPC system uses a modular hardware system design method. Except for the independent development of the hardware acceleration module and its control module, the other modules are implemented by software or IP provided by Xilinx development tools. Hardware acceleration IP adopts a top-down design method, provides parallel operation of multiple operation components, and uses pipeline technology, which speeds up data operation, so that only one operation cycle is required to obtain an operation result. In terms of recognition algorithm, a more effective training algorithm is proposed, Genetic Continuous Hidden Markov Model (GA_CHMM), which uses genetic algorithm to directly train CHMM model. It is to find the optimal model by encoding the parameter values of the CHMM and performing operations such as selection, crossover, and mutation according to the fitness function. The optimal parameter value after decoding corresponds to the CHMM model, and then the English speech recognition is performed through the CHMM algorithm. This algorithm can save a lot of training time, thereby improving the recognition rate and speed. This paper studies the optimization of embedded system software. By studying the fixed-point software algorithm and the optimization of system storage space, the real-time response speed of the system has been reduced from about 10 seconds to an average of 220 milliseconds. Through the optimization of the CHMM algorithm, the real-time performance of the system is improved again, and the average time to complete the recognition is significantly shortened. At the same time, the system can achieve a recognition rate of over 90% when the English speech vocabulary is less than 200.
Highlights
English speech recognition is a branch of pattern recognition, which is an interdisciplinary subject integrating microelectronics, communications, computers, automation, and acoustics [1, 2]. e most important technology of English speech recognition is the construction of speech signal processing technology and training model. e ultimate goal is to hope that humans can communicate with computers. is kind of human-computer dialogue scenes often appears in science fiction movies
From the specific process of English speech signal preprocessing and endpoint detection, feature extraction, English speech recognition training, and recognition, the English speech recognition system based on the improved algorithm is explained. is paper tests the embedded English speech recognition system based on DSP and discrete HMM (DHMM)
In order to complete a larger-scale System on Programmable Chip (SOPC) system, the design often adopts a top-down (Top-Down) hierarchical design idea. e hierarchical design idea is to divide a larger system into several subsystems, each subsystem is designed independently, and each subsystem is designed to be assembled into a complete system. e wiring between each functional submodule is as few as possible, the interface function is clear, and the scale of the functional module is required to be moderate. is design method greatly reduces the design complexity of system
Summary
English speech recognition is a branch of pattern recognition, which is an interdisciplinary subject integrating microelectronics, communications, computers, automation, and acoustics [1, 2]. e most important technology of English speech recognition is the construction of speech signal processing technology and training model. e ultimate goal is to hope that humans can communicate with computers. is kind of human-computer dialogue scenes often appears in science fiction movies. With the rapid development of semiconductor technology, the continuous increase in the scale of integrated circuits, and the continuous improvement of various development technology levels, English speech recognition technology has gradually become smaller after being combined with embedded systems based on DSP, FPGA, ASIC, Mathematical Problems in Engineering and other devices. In order to achieve an English speech recognition system with excellent performance, on the one hand, it is necessary to study the theory and algorithm of English speech recognition to solve and improve various problems in the recognition process. This article introduces the selection of peripheral devices of the English speech recognition control system, the selection of processors, memories and buses that make up the SOPC system, and so on. From the specific process of English speech signal preprocessing and endpoint detection, feature extraction, English speech recognition training, and recognition, the English speech recognition system based on the improved algorithm is explained. After the optimization of fixed-point and CHMM algorithm, the average real-time response speed of the system has been improved
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
