Re:Andrew Ng on the state of deep learning at Baidu
by anko on Monday February 02, 2015 @09:58PM
(#8988625)
Andrew is simply saying (if I read him correctly) that if you use generative models you might classify sounds into something other than Phonemes on one layer, and that classification may actually be better than "Phonemes" for recognising sounds. Phonemes are a construct for us to express a concept with language, but might not be the best way to represent a sound in a machine. So why try to write the routines to map sounds to phonemes when you can train it to just learn the categories that help it understand how to recognise the sounds better.
Re:Andrew Ng on the state of deep learning at Baidu
by yongjik on Monday February 02, 2015 @10:53PM
(#8988768)
Hmm, OK, that sounds much more reasonable. :)
Re:Andrew Ng on the state of deep learning at Baidu
by klipt on Tuesday February 03, 2015 @02:41AM
(#8989296)
> However, no serious NLP researcher would suggest building a text-to-speech system by getting rid of the middle OCR layer and just hooking the raw image directly to the expected sound. (Well, at least I think so, but I'd be glad to know if I'm wrong.)
Perhaps you're thinking mainly of Western writing systems?
Presumably since Andrew now works for Baidu, he is particularly interested in reading Chinese. The interesting thing about Chinese is that, as I understand it, the same symbols can have different pronunciations in different dialects, but all pronunciations mean the same thing.
I.e. the symbol has a unique meaning, but multiple possible sounds. Which implies the sound isn't really what's important here.
However, no serious NLP researcher would suggest building a text-to-speech system by getting rid of the middle OCR layer and just hooking the raw image directly to the expected sound. (Well, at least I think so, but I'd be glad to know if I'm wrong.)
Phonemes are absolutely imposed on human babies. Sure, they wouldn't know the word "phoneme", but that doesn't make the concept any less real. Imagine how a typical education on reading/writing would start like: "This is G. It is used for words like grass, game, and girl. Actually, it can also be used for gem or genie!"
Can you imagine an English-speaking child listening to this and not immediately understanding that there are two distinct sounds involved, that the first sounds for "grass", "game", and "girl" are somehow the same (even though the waveforms are different), and that this sound is somehow different from that of "gem" or "genie"? If a child doesn't understand it, then the child probably needs a speech therapy.