Artificial Intelligence/digital form of sound

Advertisement


Question
sir,
plz do answer my questions, I believe you nkow the answers.

111. suppose i say 'k'. then a sound wave is generated and if a persons eardrum comes in its way, he would listen-'k'. now the sound wave does not die out completely as soon as he has listened it once.The disturbance (wave) live even after he has listened it once, so why does not one listen it again.like -'kkkkk....' until the wave dies out completely?
is the answer is that sound wave only has a front end and no continuos body like the waves on water surface?

222. I aspire to make a software where you can transfer the words spoken by one person into the voice of some another person.am i clear in my question? i mean i would input a sound file(suppose a speech by einstien) and the output would be a sound file( say, the same speech in voice of mahatma gandhi).  

Answer
1st question:  I beleive the duration of a sound wave (it's length) is directly related to the duration of the speaker's production of that sound.  Therefor - the 'k' sound is very short - it does not persist for very long.  Any lingering after sounds would be at a very small amplitude and not be audiable.  

2nd question:  I know about natural language processing and a little about speech recognition.  You are asking a question way out of my area.  I suggest you contact the Oregon state university speach program (I may have that name wrong - there are two colleges in Portland that have 'Oregon' in there name)  anyway - they do stuff like what you are talking about.  

Artificial Intelligence

All Answers


Answers by Expert:


Ask Experts

Volunteer


Chuck Cosby

Expertise

I can answer questions about speech recognition and natural language understanding. I am particulary strong in knowedge based natural langauge techniques. I cannot answer questions about robotics, nueral nets, prolog, or vision recognition - just speech and natural language.

Experience

I have spent 25 years developing natural language software products. I have never developed speech systems, but I have developed sophisticated interfaces from natural language to speech. I have been working with speech recognition systems also for 25 years.

©2012 About.com, a part of The New York Times Company. All rights reserved.