@A.T.: Thanks a lot! > Impressive. How about pairs of similar, 3-syllable and 4-syllable words?
Well, the general idea is to look at the frequency spectrum at each point in time and try to classify it. Then link things together along the time line. Yes, it's still a lot of research TBD :) But what I like about my approach is that everything can be nicely visualized. I envision humans and AI developing algorithms together. In the end, I expect a generated recognition algorithm to consist of about a page of source code, plus a collection of audio samples. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T9a8bacdc64e9d8f6-M8b5c12324945d0e6299f567b Delivery options: https://agi.topicbox.com/groups/agi/subscription
