r9y9/SynthesisFilters.jl

Speech Recognition

Stars
13
Rank 1,512,713 (Top 30 %)
Language
Julia
License
Other
Created almost 10 years ago
Updated over 7 years ago

r9y9/SynthesisFilters.jl

r9y9

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Speech waveform synthesis filters

SynthesisFilters

SynthesisFilters.jl provides waveform generation filters for speech synthesis, especially from mel-generalized cepstrum.

Note that this package is built on top of SPTK.jl. The package is designed to provide a Julia-like interface with a focus on speech waveform synthesis. A part of the core is re-writen in Julia language from Speech Signal Processing Toolkit (SPTK).

Features

LMADF: Log magnitude approximation digital filter for synthesis from cepstrum
MLSADF: Mel-log spectrum approximation digital filter for synthesis from mel-cepstrum
MGLSADF: Mel generalized-log spectrum approximation digital filter for synthesis from mel-generalized cepstrum
AllPoleDF: All-pole digital filter for synthesis from LPC
AllPoleLatticeDF: All-pole lattice digital filter for synthesis from PARCOR
LSPDF: LSP digital filter for synthesis from LSP

Demonstration notebook

Introduction notebook: a brief introduction to SynthesisFilters.jl. Synthesized audio examples (Japanese) are avaiable.

Supported Platforms

Linux
Mac OS X
Windows

Installation

Pkg.add("SynthesisFilters")

Related packages

MelGeneralizedCepstrums.jl: spectral paramter estimation based on mel-generalized cepstrum analysis
SPTK.jl: a thin wrapepr for the SPTK
WORLD.jl: a lightweight julia wrapper for WORLD - a high-quality speech analysis, modification and synthesis system

wavenet_vocoder

WaveNet vocoder

deepvoice3_pytorch

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

gantts

PyTorch implementation of GAN-based text-to-speech synthesis and voice conversion (VC)

Jupyter Notebook

pysptk

A python wrapper for Speech Signal Processing Toolkit (SPTK).

nnmnkwii

Library to build speech synthesis systems designed for easy and fast prototyping.

tacotron_pytorch

PyTorch implementation of Tacotron speech synthesis model.

Jupyter Notebook

ttslearn

ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python)

Jupyter Notebook

pyopenjtalk

Python wrapper for OpenJTalk

pylibfreenect2

A python interface for libfreenect2

SPTK

A modified version of Speech Signal Processing Toolkit (SPTK)

nnmnkwii_gallery

A collection of examples demonstrating how we can build speech synthesis systems using nnmnkwii.

Jupyter Notebook

gossp

Speech Signal Processing for Go (not maintained)

pyreaper

A python wrapper for REAPER

sinsy

A fork of sinsy: HMM/DNN-based singing voice synthesis system

pysinsy

Python wrapper for Sinsy

open_jtalk

A fork of open_jtalk

jsut-lab

HTS-style full-context labels for JSUT v1.1

VoiceConversion.jl

[Deprecated] Statistical Voice Conversion in Julia. See the website link for new library

icassp2020-espnet-tts-merlin-baseline

ICASSP 2020 ESPnet-TTS: Merlin baseline system

Jupyter Notebook

nnet

A small collection of neural network algorithms in Go (no longer maintained)

WORLD.jl

A lightweight julia wrapper for WORLD - a high-quality speech analysis, modification and synthesis system

MelGeneralizedCepstrums.jl

Mel-Generalized Cepstrum analysis

nlp100

Assignments for NLP 100

hts_engine_API

A fork of hts_engine_API

bayesian-kalmanfilter

Variational Baysian Kalman Filter

WORLD

A modified version of WORLD (original: http://ml.cs.yamanashi.ac.jp/world/english/index.html)

Colaboratory

Colaboratory notebooks

Jupyter Notebook

SPTK.jl

A thin Julia wrapper for Speech Signal Processing Toolkit (SPTK) API

robust_pca

Robust Principal Component Analysis

ConstantQ.jl

A fast constant-q transform in Julia

demos

Deprecated. See https://github.com/r9y9/website

naive_bayes

Naive Bayes implementation with digit recognition sample

kiritan_singing_extra

Extra resources derived from https://github.com/mmorise/kiritan_singing for DNN-based singing voice synthesis

stav

Statistical voice conversion written in Go for signal processing backend, Python for model training and parameter conversions

go-world

Go port to WORLD - a high-quality speech analysis, modification and synthesis system.

VCTK-lab

Full context labels for VCTK corpus extracted by Merlin & speech tools

RobustPCA.jl

Robust Principal Component Analysis in Julia

julia-nmf-ss-toy

NMF-based Music Source Separation Demo in Julia

REAPER.jl

A Julia interface for REAPER (Robust Epoch And Pitch EstimatoR)

dotfiles

Libfreenect2.jl

A Julia wrapper for libfreenect2

blog

Deprecated. See https://github.com/r9y9/website instead.

r9y9.github.io

BNMF.jl

Bayesian Non-negative Matrix Factorization

Jupyter Notebook

fft

A simple implementation of Fast Fourier Transform (FFT)

ita-lab

HTS-style full-context labels for ITAコーパスマルチモーダルデータベース

sandbox

media-player-demo

A Media player demonstration using Qt multimedia

docker-pytorch-apex

Docker files for Pytorch + Apex

SpeechBase.jl

Please do not use this package. SpeechBase.jl still need to be carefully designed.

FHMMs.jl

proof of concept

commonvoice-lab

HTS style full-context labels for common voice

setup

Setup script for Linux system

mnist

Go bindings for MNIST

HMMs.jl

Hidden Markov Models in Julia

demos-src

Deprecated. See https://github.com/r9y9/website

pcdio_test

HTSEngineAPI.jl

A Julia wrapper for hts_engine_API

python-neural-net-toy-codes

Feed forward Neural Networks with XOR and MNIST examples

css10-lab

HTS-style full-context labels for CSS 10 Ja corpus

svdd2024seg