Font Size: a A A

Design And Implementation Of Isolated Word Recognition System Based On FPGA

Posted on:2013-08-02Degree:MasterType:Thesis
Country:ChinaCandidate:J J LuoFull Text:PDF
GTID:2298330467978479Subject:Circuits and Systems
Abstract/Summary:PDF Full Text Request
With the continuous development of speech recognition,how to improve the speech recognition of pronunciation form has become the main problem to be solved in the aspect.Compared to the speech recognition of continuous word,the recognition of isolated words need the algorithm of voice activity detection and template matching with a higher accuracy.In this way,isolated words can be separated from sentence,so how to improve the recognition of isolated word become a difficult and meaningful issue.Except the reliability of recognition algorithm,people made a higher demands on miniaturization,convience and improvemence of device,so it has much practical applicability to recognize speech with the help of embedded systems.According to the demand, this article proposes a design about embedded soft-core processor speaker recognition system based on SOPC and Nios II.Through the comparision of arithmetics about isolated words speech recognition,the key of this design depends on DTW model based on dynamic programming and it designs and realizes the isolated words speech recognition system on SOPC(System on Programmable Chip).Moreover,because the system needs plenty of highspeed calculation,through the design,the author makes full use of abundant hardware multipliers.The actionable outcomes includes timely collection of voice signals and voice activity detection, the highspeed fixed-point256points FFT module and module,DCT discrete cosine transform module and so on.Meanwhile,with the data signals transferred to NiosII soft core by Avalon bus, software realizes the read arithmetic of FAT root direction,generation arithmatic of random datas and template matching arithmetic based on DTW model and so on.In the end, author designed a man-machine interface with SOPC characteristics,such as suggesting feedback information on LCD and finished custom-defined system which can be offered by Altera’s driving interface.Test showed that the function of hardware is effectively、feasible, software and hardware work together to achieve data collection, storage and processing on FPGA. The system as embedded systems is easy to program, debug and easy to use. This system has a very high cost-effective, can saving software and hardware resources, has good application prospects.
Keywords/Search Tags:Speaker recognition, Isolated words, DTW, Nios Ⅱ
PDF Full Text Request
Related items