Dissertation > Excellent graduate degree dissertation topics show

Speech Input Solution Research Based on Cloud Computing

Author: LuoXi
Tutor: LiuJinGao
School: East China Normal University
Course: Communication and Information System
Keywords: Cloud Computing Speech Recognition GAE HMM Sphinx4
CLC: TN912.34
Type: Master's thesis
Year: 2010
Downloads: 493
Quote: 2
Read: Download Dissertation

Abstract


Not all the computer application is suitable to immigrant to cloud computing, however the agile and economic cloud computing do give companies a new vision of deploying application and data storage. Enhancement of internet environment plus break through and standardization of cloud computing techniques will make the cloud era which transfer current local computing and storage to remote cloud server pretty feasible. In general, the value of Cloud Computing is not just about cost reduction; the value also comes from standardization, collaboration and globalization.The most stable and efficient speech recognition algorithm is HMM(Hidden Markov Model), thus almost all the robust speech recognition system based on HMM. Speech application has many functional scenarios, however, it rare used as a computer inputting method. One reason is the error rate of continuous speech recognition is too high to work as an common inputting method. The other reason is the speech recognition software is too big comparing to other popular inputting applications. Deploying it on a PC is inconvenient. This paper tried to solve the second reason and make speech inputting a convenient way for end users.I have transplanted HMM based open sourced speech recognition system Sphinx4 to GAE (Google Application Engine), so a speech recognition system can be used just by typing a URL in a browser. A Java applet collects speech data and sends to servlet on GAE, the servlet on the GAE recognizes the speech and sends the result back to the applet. This solution makes speech recognition easily available and all the newer versions will be presented to users without any upgrading cooperation from users.

Related Dissertations

  1. Multiple ANN/HMM Hybrid Used in Speech Recognition,TN912.34
  2. The Design of a DSP-Based Robot Speech Command Recgnition System,TN912.34
  3. The Research of Dynamic Trust Model on Cloud Computing Platform,TP309
  4. Measurement and Reconstruction of Ion Channel Current for Cell Membrane in Rat’s Cerebral Cortex,Q42
  5. A Research on Speech Recognition Technology,TN912.34
  6. Research and Implementation on Model of Educational Knowledge Service System Based on Eucalyptus,TP393.09
  7. Research of Handwriting Input Method Based on Computer Vision,TP391.14
  8. The Research for Fractal Feature Extraction and Face Recognition Algorithm,TP391.41
  9. The Crawler of Education in Web by Cloud Computing,TP391.3
  10. Design of the Mobile Learning System Based on Hadoop,G434
  11. Voice recognition in the access control application,TN912.34
  12. Rule-based Web text information extraction technology research,TP391.1
  13. Google cloud- based B2C website background management module,TP311.52
  14. Digtital Image Processing Platform Baseed on Cloud Computing,TP391.41
  15. HMM-based Connection between the Social Network Analysis,F49
  16. The Research on Fault Diagnosis Method Based on Continuous Hidden Markov Model with Feature Weighted,TH165.3
  17. Complex environment speech enhancement method,TN912.35
  18. An Hmm-based Speech Synthesis System Applied to Tianjin Dialect,TN912.33
  19. A Survey of Hidden Markov Model Based Clustering Algorithm on Time Series,TP311.13
  20. Research on Hmm-based Speech Recognition System of the Robot,TN912.34
  21. The Study of Cough Signal Recognition Based on HMM-ANN Hybrid Model,TN912.34

CLC: > Industrial Technology > Radio electronics, telecommunications technology > Communicate > Electro-acoustic technology and speech signal processing > Speech Signal Processing > Speech Recognition and equipment
© 2012 www.DissertationTopic.Net  Mobile