All by James Hague
Recovering from a Computer Science Education
Your Coding Philosophy is Irrelevant
Photography as a Non-Technical Hobby
Arthur
Understanding your own code by Eli Bendersky
I will add, if you need to maintain a certain codebase, go ahead to read all of them.
Arthur
There are couple of messages on open source speech recognition on iOS. That certainly caught my eyes. For now, I believe one of most well-known names is OpenEars. It is built up on PocketSphinx and it provides speech synthesis functionalities as well.
It looks pretty promising. So I will probably start to play with it as well.
I just added a link of OpenEars here in the Grand Janitor’s Blog. Btw, I should think of better syndicate different ASR-related site.
Arthur
Categories
Readings at Jan 4, 2012
Forth language from James Hague (Link)
Arthur
Categories
Words of the day
English: violescent, diffident.
Both are related to simpler, commonly used words.
Categories
Readings of Jan 3, 2013
I tried to gather some topic ideas on this blog. From LinkedIn, I hear quite a bit of feedbacks on discussion about decoding algorithms. I have thought about this a bit. Here are some sample topics which I will discuss,
- How to setup Recognizer X on a Platform Y?
- What are the interesting properties of Program A in speech recognition package B?
- What are the best practice when you try to use a certain model training package?
- Tuning results in a domain.
- News: certain package has a new version coming out! What are something special?
- Thoughts in speech recognition problem.
- Thoughts in programming problem.
- Algorithms/Data structures for decoding/parameter estimation : like you suggested in this post.
- What is an interesting development direction for a speech recognition package?
- Others: softwares/algorithm in some related fields such as NLP, MT.
Of course, I will keep on chatting about some on-going components of Sphinx which I feel interested,
- Sphinx 4 maintenance and refactoring
- PocketSphinx’s maintenance
- An HTKbook-like documentation : i.e. Hieroglyphs.
- Regression tests on all tools in SphinxTrain.
- In general, modernization of Sphinx software, such as using WFST-based approach.
Unlike academic journals, I hope this is more an informal hub of ASR information. I don’t know if I can keep on. but at least that’s what I am going to try.
In any case, this blog will occupy much of my spare time next year. Feel free to comments and give me suggestions. And of course ……. Happy New Year!
Arthur
Spanish: riesgo
English: promulgate, sagacious
Esperanto : Ekstermensigu
Toki Pona: All 121 words of it. Liking them in a day should be okay.
To me, I always try to think how we can build a recognizer for make-up language such as Esperanto, Toki Pona or Klingon.
Arthur
Not exactly news, it happened 6 days ago.
See this thread:
http://www.speech.sri.com/pipermail/srilm-announce/2012q4/000010.html
Looks pretty good. I thought that the toolkit would be stagnated but now I am glad that it is maintained. There seems to be many bug fixes.
Goodies: Web Ngram from MS: http://web-ngram.research.microsoft.com/
Linux Chews Up Kernel Maintainer for Introducing UserSpace Bug.
http://developers.slashdot.org/story/12/12/29/018234/linus-chews-up-kernel-maintainer-for-introducing-userspace-bug
That’s just the way it is. Remember, there are always better, stronger, more famous, more powerful programmers working with you. So criticisms will come one day.
My take, as long as if you don’t work with them in person, just treat them as an icon on the screen. π
Arthur