Takaaki-Saeki

ssl_speech_restoration

SelfRemaster: SSL Speech Restoration

DiscreteSpeechMetrics

Reference-aware automatic speech evaluation toolkit

zm-text-tts

[IJCAI'23] Learning to Speak from Text for Low-Resource TTS

simplified_neural_source_filter

PyTorch implementation of simplified neural source filter model (s-nsf)

ssl_speech_restoration_v2

SpectralFitting

Curve fitting to complicated spectrum by using scipy.optimize and lmfit

espnet

End-to-End Speech Processing Toolkit

Karman

Final project of aerodynamics2D

SpeechMOS

Easy-to-Use Speech MOS predictors

Algorithms

Practice of basic algorithm

arXivNotifier

Under construction

BoundaryLayerFlow

Final project of aerodynamics2C

CurveFitting

Implementations of basic algorithm of curve-fitting

dotfiles

FastSpeech2-JSUT

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

GNN

Implementation of Graph Neural Net

hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

jtubespeech

LipNet

Keras implementation of 'LipNet: End-to-End Sentence-level Lipreading'

MLbasics

Implementations of basic machine learning algorithms (Asobi)

NISQA

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

p4

Practice for p4

pytorch-tutorial

PyTorch Tutorial for Deep Learning Researchers

shinjiwlab.github.io

speechlmscore_tool

Takaaki-Saeki

Config files for my GitHub profile.

webTask

M1s授業用