speech-recognition-transfer-learning

Code for TensorFlow Speech Recognition Challenge on Kaggle
Based on Listening to the World Improves Speech Command Recognition[1]
Transfer learning from UrbanSound8k dataset to Speech Commands dataset[2]

Easy download UrbanSound8k dataset with
wget https://serv.cusp.nyu.edu/files/jsalamon/datasets/UrbanSound8K.tar.gz

References

[1] Brian McMahan, Delip Rao - arXiv:1710.08377v1
[2] "Warden P. Speech Commands: A public dataset for single-word speech recognition, 2017. Available from http://download.tensorflow.org/data/speech_commands_v0.01.tar.gz"