A speech recognition and synthesis tool

ABSTRACT

Many of the new technologies designed to help worldwide communication -- e.g. telephones, fax machines, computers -- have created new problems especially among the hearing and visually impaired. A person, who has severe hearing impairments, particularly to the extent in which deafness occurs, may experience difficulties communicating over a telephone as he or she is unable to hear the recipient's responses. Conversely, someone with visual impairments would have little inconvenience using a telephone but may not be able to communicate through a computer because of the difficulties (or, in the case of blindness, impossibility) in reading the screen. The goal of this project is to develop a Speech Recognition and Synthesis Tool (SRST) that provides a solution to the communication between the hearing and visually impaired. SRST is free and does not require any additional equipment besides a computer. Additionally, SRST can be used in educational settings, regardless of students' or teachers' disabilities, as a teaching aid.

REFERENCES

• 1: Freedom Scientific, "FSTTY Deaf-Blind Solution Pricing," {Online}, Available: http://www.freedomscientific.com/fs_products/fsttypricing2.asp
• 2: Black, Adam, et al., "Festival Speech Synthesis System," {Online}, Available: http://www.cstr.ed.ac.uk/projects/festival/
• 3: "The CMU Sphinx Group Open Source Speech Recognition Engines," {Online}, Available: http://cmusphinx.sourceforge.net/html/cmusphinx.php
• 4: Cumming, Murray, et al. "Gtkmm - the C++ Interface to GTK+," {Online}, Available: http://www.gtkmm.org/
• 5: Lantinga, Sam, Masahiro, Minami, and Wood, Roy. "SDL_net Documentation Homepage," {Online}, Available: http://jcatki.no-ip.org/SDL_net/
• 6: Michael F. McTear, Spoken dialogue technology: enabling the conversational user interface, ACM Computing Surveys (CSUR), v.34 n.1, p.90-169, March 2002 [doi>10.1145/505282.505285]
• 7: "ModelTalker Synthesizer, Speech Research Lab," {Online}, Available: http://www.asel.udel.edu/speech/ModelTalker.html
• 8: "Ventrilo -- Surround Sound Voice Communication Software," 2005. {Online}, Available: http://www.ventrilo.com/
• 9: Brusilovsky, Peter. "Adaptive and intelligent technologies for web-based education". Special Issue on Intelligent Systems and Teleteaching, (Kunstliche Intelligenz), 4:19--25, 1999.
• 10: Bulyko, Ivan and Ostendorf, Mari. "The Impact of Speech Recognition on Speech Synthesis," 2002. Proceedings of 2002 IEEE Workshop on Speech Synthesis, 2002.
• 11: A. Le et al., "The 2002 NIST RT Evaluation Speech-to-Text Results," Proc. RT02 Workshop, 2002. Available: http://www.nist.gov/speech/tests/rt/rt2002/
• 12: "Cygwin Information and Installation," {Online}, Available: http://www.cygwin.com/
• 13: Ravishankar, Mosur K. "Sphinx-3 s3.X Decoder (X=5)," {Online}, Available: http://cmusphinx.sourceforge.net/sphinx3/

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.1 Multimedia Information Systems

General Terms:
Human Factors, Performance

Keywords:
human computer interaction, speech recognition, speech synthesis, tools for visually and hearing impaired, web-based education