Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Curated list of speech and natural language processing resources

github.com

Post reply on HN
Print view View original

11–20 of 28 posts

Re: Curated list of speech and natural language processing resources

#11

Post by nl »

motdiem wrote: post #4
m_eiman wrote: post #2

About the "Text-to-Speech" section there, I was really impressed with the updated Swedish "Alva" voice in OSX El Capitan: it correctly pronounces "tomten" in different ways in the first and second occurrence in this example: say -v Alva "Tomten dricker julmust på tomten" "Tomten" can mean either "Santa Claus" or "the yard"/"the plot" depending on context, and apparently they're able to detect this properly.

OS X makes progress with every release on this front. I typically test it with a few tricky french sentences (think "les poules du couvent couvent") and it seems to improve, but it's hard to say from the outside what gets better in the model ("Mes fils ont cassé mes fils" still fails for instance, but seems harder to detect to me)

I think the OP was talking about Text-to-Speech, and you are (maybe?) talking about speech recognition?

(The irony of this misunderstanding being kicked off by a comment about the text-to-speech engine understanding the context of a word amuses me)

Re: Curated list of speech and natural language processing resources

#13

Post by nl »

https://github.com/facebook/MemNN should be in the language modelling (or Deep Learning) part. I'll give them a pass because it was only released a couple of days ago.

The original Word2Vec[1] is missing too. While Gensim and Glove are nice, Word2Vec still outperforms them both in some circumstances.

Surely there is a good LTSM language modelling project somewhere too? I can't think of one off the top of my head though. There's some code in Keras[2], but maybe Karpathy's char-RNN would be better[3] because of the documentation.

[1] https://code.google.com/p/word2vec/

[2] https://github.com/fchollet/keras/blob/master/examples/lstm_...

[3] https://github.com/karpathy/char-rnn

Re: Curated list of speech and natural language processing resources

#14

Post by michael_h »

nl wrote: post #13

https://github.com/facebook/MemNN should be in the language modelling (or Deep Learning) part. I'll give them a pass because it was only released a couple of days ago. The original Word2Vec[1] is missing too. While Gensim and Glove are nice, Word2Vec still outperforms them both in some circumstances. Surely there is a good LTSM language modelling project somewhere too? I can't think of one off the top of my head thou…

LSTM --> right now, Torch 7 and Theano are receiving the bulk of the attention.

Re: Curated list of speech and natural language processing resources

#15

Post by hendler »

michael_h wrote: post #14
nl wrote: post #13

https://github.com/facebook/MemNN should be in the language modelling (or Deep Learning) part. I'll give them a pass because it was only released a couple of days ago. The original Word2Vec[1] is missing too. While Gensim and Glove are nice, Word2Vec still outperforms them both in some circumstances. Surely there is a good LTSM language modelling project somewhere too? I can't think of one off the top of my head thou…

LSTM --> right now, Torch 7 and Theano are receiving the bulk of the attention.

Keras is based on Theano - an easy way to get started.

Re: Curated list of speech and natural language processing resources

#19

Post by mohn »

I'm glad to see the CMU pronouncing dictionary in there. It was instrumental when I wrote a web app[1] to generate Spoonerisms[2] (my apologies for the UI and the fact that I haven't yet removed the more obscure words, especially obscure homophones, from my cmudict subset).

The cmudict isn't under the text-to-speech subheading in this list, but I think the folks at Carnegie Mellon may have considered text-to-speech applications, like a talking GPS navigator, when they compiled the dictionary. I recall the cmudict containing lots of US city names.

[1] https://spoonerizer.appspot.com/

[2] https://en.wikipedia.org/wiki/Spoonerism

Re: Curated list of speech and natural language processing resources

#20

Post by gbrits »

Consider a speech-to-structured-search-app in a limited domain, like a specialized siri/google now. For example something like a real estate search assistant with possible questions like: "what new 2 bedroom apartments have become available in Capitol Hill, Seattle this week?"

Perhaps naively, it seems a big part of the deducing meaning could be done doing ordinary dictionary lookups with terms like 'bedroom', 'apartments', "Capitol Hill", "seattle" etc.

Is this indeed naive, or is this 'dictionary lookup'-technique part of the bag of tricks used? If so, any good references to use this in combination with other techniques described here?

Highly interested in this topic, but looking for a nice introduction to get used to the terminology of the field.

Post reply on HN