Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: Elmer who wrote (37563)	10/24/1997 9:14:00 PM
From: Barry Grossman	Read Replies (1) \| Respond to of 186894

Elmer, I'm not qualified in those chip or software technologies to know enough to explain how or where in the computer the job gets done, but I'd guess some combo of the two will accomplish economic VR for the masses in the next 5 years. As I've said many times before, even my wife will then be able to use a computer. The market will open up to users who would never input a computer any other way. Care to guess how many that might be? bg

To: Elmer who wrote (37563)	10/25/1997 8:51:00 AM
From: Dave	Respond to of 186894

Elmer: RE: Voice Recognition The area is divided into two parts: Voice Recognition and Speech Recognition. You use Voice Recognition when you want to identify someone's particular voice patterns. Speech Recognition is to change spoken words into text words on the computer. There are many different algorithms out on Voice/Speech Recognition. In a word, there are many syllables. To recognize the words, the algorithm breaks the word down further into a phoneme and starts the recognition process. Some of the algorithms use probabilistic theory, trees, huge data bases, a method called the Hidden Markov Model, etc. This technology is huge. Think about a Chinese, Japanese, or Korean person. Their written language is made up of symbols. In each respective language, they must have tens of thousands of symbols, right? Anyways, using a keyboard would be very inefficient. Wouldn't it be more efficient if one could speak into a microphone and the symbol appears on the screen? As for the hardware, most of these highly specialized Speech/Voice Recognition programs use a DSP chip either from Analog Devices or TI. The less complex ones, such as programs for home use, use a 486 or greater CPU..... Hope that helps.... dave