Hirofumi Inaguma's repositories
tensorflow_end2end_speech_recognition
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)
asr_preprocessing
Python implementation of pre-processing for End-to-End speech recognition
domain-transfer-network
TensorFlow Implementation of "Unsupervised Cross-Domain Image Generation"
wer_are_we
Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.