StackOverflow2013

Note that there are some explanatory texts on larger screens.

plurals

PO
text
Body
copied!<p><strong>Regarding LM Formats:</strong></p> <p>AFAIK most Language Models use the ARPA standard for Language Models. Sphinx / CMU language models are compiled into binary format. You'd need the source format to convert a Sphinx LM into another format. Most other Language Models are in text format.</p> <p>I'd recommend using the HTK Speech Recognition Toolkit ; Detailed Documentation here: <a href="http://htk.eng.cam.ac.uk/ftp/software/htkbook_html.tar.gz" rel="nofollow">http://htk.eng.cam.ac.uk/ftp/software/htkbook_html.tar.gz</a></p> <p>Here's also a description of CMU's SLM Toolkit: <a href="http://www.speech.cs.cmu.edu/SLM/toolkit_documentation.html" rel="nofollow">http://www.speech.cs.cmu.edu/SLM/toolkit_documentation.html</a></p> <p>Here's an example of a language model in ARPA format I found on the net: <a href="http://www.arborius.net/~jphekman/sphinx/full/index.html" rel="nofollow">http://www.arborius.net/~jphekman/sphinx/full/index.html</a> </p> <p>You probably want to create an ARPA LM first, then convert it into any binary format if needed.</p> <p><strong>In General:</strong></p> <p>To build a language model, you need lots and lots of training data - to determine what the probability of any other word in your vocabulary is, after observing the current input to this point in time.</p> <p>You can't just "make" a language model by just adding the words you want to recognize - you also need a lot of training data (= typical input you observe when running your speech recognition application). </p> <p>A Language Model is not just a word list -- it estimates the probability of the next token (word) in the input. To estimate those probabilities, you need to run a training process, which goes over training data (e.g. historic data), and observes word frequencies there to estimate above mentioned probabilities.</p> <p>For your problem, maybe as a quick solution, just assume all words have the same frequency / probability.</p> <ol> <li><p>create a dictionary with the words you want to recognize (N words in dictionary)</p></li> <li><p>create a language model which has 1/N as the probability for each word (uni-gram language model)</p></li> </ol> <p>you can then interpolate that uni-gram language model (LM) with another LM for a bigger corpus using HTK Toolkit </p>

Querying!

Guidance

An individual column

Larger individual text columns get their own page to allow for proper reading.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload