After reading about Apple's new patents for speech recognition, I am thinking that Apple will probably be including two microphones on either side of the iMac's display and Apple LCD displays. Also, one must assume that Apple is investing further in speech recognition technology for future MacOS releases or a new software title like that of ViaVoice. I would expect to see further AppleScript support for it and a bunch of new commands. Also, we may see better noise filtering software for the OS. Now the only question is, how is Apple going to apply this to the motherboard. All sound is currently directed through the CPU, so will Apple have a new onboard sound card like device to handle the increased load? If so, maybe we can see support for Dolby digital surround sound and such. That definately would be a plus for Apple b/c they are late to jump on the bandwagon for this technology.
I also would suspect that Apple is developing this technology in part for iChat (or iSpeak as it may end up being, but could also be the title for an Apple speech recognition software), which could eliminate background sound when chatting or videoconfrencing. Speaking of iChat, I am wondering if Apple is going to have it so that the computer compresses the voice data before sending it and then decompresses it on the recieving end. This would definately be an advantage to those of us still using dial-up connections, but I am wondering if they did this, would they be able to reduce the lag caused by compression to a reasonable level. Does anyone know if the PPC 970 will have any enhanced instructions to eliminate the need for a sound card or not?
Just some thoughts. Let me know what you think.
I also would suspect that Apple is developing this technology in part for iChat (or iSpeak as it may end up being, but could also be the title for an Apple speech recognition software), which could eliminate background sound when chatting or videoconfrencing. Speaking of iChat, I am wondering if Apple is going to have it so that the computer compresses the voice data before sending it and then decompresses it on the recieving end. This would definately be an advantage to those of us still using dial-up connections, but I am wondering if they did this, would they be able to reduce the lag caused by compression to a reasonable level. Does anyone know if the PPC 970 will have any enhanced instructions to eliminate the need for a sound card or not?
Just some thoughts. Let me know what you think.