Popular GitHub Repositories for Htk

Lyrics-to-audio-alignement system. Based on Machine Learning Algorithms: Hidden Markov Models with Viterbi forced alignment. The alignment is explicitly aware of durations of musical notes. The phonetic model are classified with MLP Deep Neural Network.

Automatic speech recognition (ASR) for Indonesian language built by using HTK and Julius. Web interface is built using Node.js.

A tool for generating sub-word (phone or grapheme) level embeddings from an HTK-style MLF ASR corpus