homink

speech.ko. Korean read speech corpus (about 120 hours, 17GB) from National Institute of Korean Language

deepspeech.pytorch.ko. Python

kaldi-asr.forced_decoding. Perform the forced decoding with target transcription

kaldi-asr.ko. Shell

speech_reverb. This repository includes scripts for reverberation WAV file creation.

for_speech_scientists. Brief knowledges for speech scientists

kaldi_notes. Kaldi notes for beginners

deepvoice3_pytorch. PyTorch implementation of convolutional networks-based text-to-speech synthesis models