Hi Peter, This part of your message caught my attention.
Peter Reid wrote: > 3. Figure out how to compare the two sound clips > (sample against user), or convert the user speech input > into text for comparison with the original Word. Again, > any good ideas would be welcome, but I'm prepared to > do a bit of general research about this. Comparing two audio clips is considered a difficult task but in 1994, "Claire Interactive Musical Coach" a voice training software for 68k Macs could do this with great accuracy. https://www.wired.com/1994/03/sing-directly-into-the-mac/ Of course, that software was created by Opcode engineers. The same people who at that time was creating the best audio software for Mac. (Later, many of them started working for Apple) Today, hardware is much more powerful than 68k macs so you could be sure that this task is much easier now than it was 23 years ago. https://wiki.musicbrainz.org/Fingerprinting Maybe, just maybe, you could convert user recorded audio into an image (or line graph) and compare this against the image or line graph of original audio sample. Al _______________________________________________ use-livecode mailing list use-livecode@lists.runrev.com Please visit this url to subscribe, unsubscribe and manage your subscription preferences: http://lists.runrev.com/mailman/listinfo/use-livecode
