Kanru Hua

pytorch-softdtw. An implementation of SoftDTW for PyTorch.

libllsm2. Low Level Speech Model (version 2.1) for high quality speech analysis-synthesis

SHIRO. Phoneme-to-speech alignment toolkit based on liblrhsmm

prometheus-spark. Learn or die.

ciglet. Lightweight signal processing library for audio and speech applications

Rocaloid-old. OBSOLETED! Moved to http://github.com/Rocaloid

libpyin. pYIN implementation for fundamental frequency estimation

libllsm. Low Level Speech Model for high quality speech analysis-synthesis

nebula. Zero-data (yet trainable) probabilistic fundamental frequency estimator.

libgvps. Generic Viterbi Path Searcher

libutaust. Parsing and writing UST (UTAU Sequence Text) files in C.

liblrhsmm. Left-to-right Hidden Semi-Markov Model implementation in C

CVEDSP. (Obsoleted) A speech signal processing library designed for CVE of Rocaloid Project.

deadfish. A very simple audio editing tool.

mrq. Code snippet for reading & writing Moresampler's .mrq file

IB-EE-FFT. My International Bacculaurate Extended Essay on Fast Fourier Transform Implementation.

World. A high-quality speech analysis, manipulation and synthesis system

CVEANN. (Obsoleted) Artificial Neural Network library for Rocaloid Project.

world-octave. Blazingly fast World speech synthesis for GNU Octave

hmm-workshop. Materials for a workshop on hidden Markov model

JUCE. The JUCE cross-platform C++ framework.