the machine learning equivalent of Excalibur is only shallow in the lake. But it takes guts to believe in it.
My audio recog program goes as follow-> a) Run it per sample, to get all overlaps. b) do a knn match to a database, if it isnt near enough to any of them, you store it as a new class. (so its unsupervised learning, at least this part of it.) c) you then you should get back a slur of phonemes, and u have to take out the runs, till your left with just the words, which are separated by short silences maybe. - then (i havent actually done it yet) I guess I have to match it to manual subtitles (labelled data), until it can convert everything. Its half unsupervised. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T89dc799e249e2d0b-M02cb7049f10a2c63c257916e Delivery options: https://agi.topicbox.com/groups/agi/subscription
