Voice-recognition system
This page is being edited by Jetske Tamboezer EMBA09. In case of any questions/remarks contact me.
Description:
Speech recognition technology and natural-language-processing technology have long been studied as input-and-output technology for electronics. However, use of speech recognition technology is still limited because the system can only recognize speech with clear and slow pronunciation. Regrettably, present technology cannot recognize conversation among multiple people or naturally spoken conversation. Many other conventional interfaces of information machines and equipment require a certain amount of mastery. Until now, there is no established interface with which people can communicate with other people easily in a natural form. With the wide speared of internet, many information devices like personal computers, mobile phones or PDAs are becoming widely used. A development of user-friendly information device, which can be used by anyone, anywhere and easily, is required for not only those who are good at computers but also those who are beginners and elderly people. As one of the basic technology to realize the information device, development of advanced speech recognition technology and natural-language-processing technology is widely brought to attention.
Enablers:
Factors which strengthen this driving force. (these are actually other driving forces, and you can link to them in the wiki!)
1. Aging people
2. Deteriorating security, especially for children
3. Globalization
4. Broadbandization
5. Popularity of car navigation system
Inhibitors:
Factors which weaken this driving force. (these are actually other driving forces, and you can link to them in the wiki!)
1. Technical difficulties (Phonological recognition, extraction of intent, etc)
Paradigms:
Users of internet will exponentially increase because anyone in any age group with any skill of computer can utilize internet.
Use of internet will exponentially increase when people can access and retrieve information through only voice.
By combining voice recognition system and translation system, people can access all the necessary information in any part of the world from anywhere.
Information available in website will exponentially increase because all spoken languages can be directly in storage in web space.
Experts:
Sources for additional information about this driving force. (if you have found people, put the links to them)
William S. Meisel, Ph.D., president of TMA Associates
Prof. Hiroaki Sakoe, Dept. of Intelligent Systems, Kyushu University
Timing:
1952 Bell Communications Research started to investigate speech recognition with zero crossing
1959 Kyoto University, Japan, developed “speech-recognition typewriter” utilizing the technology Bell Communication research developed.
1970s Russia and Japan simultaneously developed DP matching method, which normalizes utterance time length by using dynamic programming
1990s Defense Advanced Research Projects Agency, U.S, started dictation program for speech recognition, which realized Q&A voice recognition system by n-Gram method