Theory on Real Time and Automatic Sound-to-Text Transcription
(a little warning: I'm not native to English language, but ASL is.)
I recently started learning the C++ language. I needed a "problem" to be a motivation factor for purpose and reason for programming.. so the problem I picked is sound to text. The below link will take you to my theory webpage about real time sound-to-text transcription technology. My work on it is on-going process. I'll admit that right now the theory is not fully plausible one.. but I still want you to just maybe check it out, give feedback, and or make comments which could help "solidify" my understanding and researching on either or both C++ programming and ways of developing solution(s) to problems.
Before learning how to do C++ programming I realized that I needed to know the real reason why and purpose for doing it. There are many different kinds of problems that can become the motivation factor behind reason and purpose for development of programs. Picked problem to focus on: Sound to text. Why? I'm deaf. First of all I'm generally happy, satisfied, and grateful with most videos, tv shows, and even some computer games that have closed captioning or subtitle and even Google is working on youtubes with cc. But not all are perfect or even close to good. After spending some time researching on the net I figured out that currently the sound-to-text transcription in automatic and real time is still not fully reliable and accurate. Also the availability of automatic and real-time sound-to-text transcription is not always the case in every application/programs, in games (offline and online), videos, etc. I figure.. why not take it further and make it fully possible to have an automatic and real time transcription of sound to text, that would make things so much easier for many people. Once that kind of technology is fully developed, it could be integrated into existing applications, games, etc.
Update with New Information
New information: I realized that I was theorizing about a few different technologies based on universal translation and transcription concept, not one. So, I have created a separate theory for each technology, also each with a diagram on my webpages. There are currently 6 total different theorized technologies.
1. Universal Translator One Way Technology -> link: http://www.tylersnider.ca/univ_trans...eway_tech.html
2. Universal Translator Bidirectional Technology -> link: http://www.tylersnider.ca/univ_translator_bid_tech.html
3. Universal Transcription One Way Technology -> link: http://www.tylersnider.ca/univ_transc_oneway_tech.html
4. Universal Transcription Bidirectional Technology -> link: http://www.tylersnider.ca/univ_transc_bid_tech.html
5. Universal Translation and Transcription One Way Technology -> link: http://www.tylersnider.ca/univ_trans...eway_tech.html
6. Universal Translation and Transcription Bidirectional Technology -> link: http://www.tylersnider.ca/univ_trans..._bid_tech.html
Number 6 is theoretically more powerful and interesting as it allows both persons to talk each other in either text or sound OR both in such almost SIMULTANEOUSLY way.
Additional comment about this thread: The thread posted above is really directed toward "project idea" or "theory", but it includes some concepts that will lead to building or programming of an application so that's why I posted the thread under computer programming, as there is no "project idea/theory" specific forum.