Artificial Intelligence Depot
Visiting guest. Why not sign in?
News, knowledge and discussion for the AI enthusiast.
FEATURES COMMUNITY KNOWLEDGE SEARCH  
Get Creative: AI Article Writing Contest
Fancy the chance of getting developer focus, improving your research skills, sharing your artificial intelligence ideas, obtaining expert feedback, getting published online AND winning a prize?
Enter the AI Article Writing Contest!
Speech Recognition and Voice Synthesis
A Lethal Combination
 
Speech Recognition and Voice Synthesis

There's been three articles on these topics recently, contributing to the buzz about these promising technologies. The first article is over on the NY Times: The Last Word in Dictation. Period. It mentions a promising bit of software that uses Natural Language Processing and some other form of Pattern Recognition to determine what you want it to type. That's right, the difference is that you can just talk to it, and it'll make the changes necessary. Or at least that's the theory... the article concludes that hiring humans to do this job would probably be more productive, but at least its on the right track!

The second article is over on AgentLand, named Look Who's Talking. It takes a very interesting look into speech synthesis, comparing the alternatives available: formant synthesis and concatenation. The first creates a voice digitally, usually using phoneme pronunciation algorithms, and the second uses a big database of pre-recorded humans. This latter approach is said to obtain human-like results! The rest of the article looks into specific packages; worth a quick skim.

The last article is a promising review over on Comm Web entitled Did You Say: "You Need A Speech Rec Wireless Headset?". The software seems to be doing better!

934 posts.
Monday 28 January, 03:22
Reply