Skip to content

Neural net code for lexicon-free speech recognition with connectionist temporal classification

License

Notifications You must be signed in to change notification settings

amaas/stanford-ctc

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

stanford-ctc

Neural net code for lexicon-free speech recognition with connectionist temporal classification

This repository contains code for a bi-directional RNN training using the CTC loss function. We assume you have separately prepared a dataset of speech utterances with audio features and text transcriptions.

For more information please see the project page and the character language modeling repository

Our neural net code runs on the GPU using Cudamat We use a forked version of Cudamat to add an extra function which you can find here. If you need a more recent version of cudamat you can likely take just the extra function and apply the patch to the most recent version of Cudamat.

The latest code is in the directory ctc_fast; please set your PYTHONPATH accordingly. The script runNNet.py should be the starting point for training the BRNN model -- you'll have to modify run_cfg.py and decoder_config.py. Unfortunately the run*.sh scripts in {timit/wsj/swbd}-utils are outdated but you can refer to them for reasonable parameter settings.

Example feat#.bin, keys#.txt, and alis#.txt files for small subset of TIMIT training data can be found here.

For details about the algorithms used please see our NAACL paper. Also please cite that paper when using this code:

@inproceedings{lexfree2015,
    title={Lexicon-Free Conversational Speech Recognition with Neural Networks},
    author={Maas, Andrew L. and Xie, Ziang and Jurafsky, Dan and Ng, Andrew Y.},
    booktitle={Proceedings the North American Chapter of the Association for Computational Linguistics (NAACL)},
    year={2015}
}

About

Neural net code for lexicon-free speech recognition with connectionist temporal classification

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published