/Speech-Recognition-CTC

Speech Recognition using Connectionist Temporal Classification

Primary LanguagePython

Speech-Recognition-CTC

Speech Recognition using Connectionist Temporal Classification

Reference

Paper
  1. Connectionist Temporal Classification : http://www.gitxiv.com/posts/9hLxYvJLCu9Z9N4pK/ctc-connectionist-temporal-classification
  2. Towards End-to-End Speech Recognition with Recurent Neural Network : https://arxiv.org/abs/1701.02720
  3. Lexicon-Free Conversational Speech Recognition with Neural Network : http://deeplearning.stanford.edu/lexfree/lexfree.pdf
  4. Wavenet : https://arxiv.org/pdf/1609.03499.pdf
Code
  1. Beam decode with Language Model(LM) : https://github.com/amaas/stanford-ctc
  2. Wavenet : https://github.com/buriburisuri/speech-to-text-wavenet/blob/master/model.py