nii-yamagishilab/project-CURRENNT-public

Stars
76
Rank 420,374 (Top 9 %)
Language Cuda
License
GNU General Publi...
Created about 6 years ago
Updated about 4 years ago

nii-yamagishilab/project-CURRENNT-public

nii-yamagishilab

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

CURRENNNT codes and scripts

project-NN-Pytorch-scripts

multi-speaker-tacotron

VCTK multi-speaker tacotron for ICASSP 2020

Capsule-Forensics-v2

Implementation of the Capsule-Forensics-v2

self-attention-tacotron

An implementation of "Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language" https://arxiv.org/abs/1810.11960

ZMM-TTS

ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations

tacotron2

An implementation of Tacotron and Tacotron2

ClassNSeg

Implementation and demonstration of the paper: Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos

project-CURRENNT-scripts

This repository contains the scripts to use CURRENNT

mos-finetune-ssl

Extended_VQVAE

Intelligibility-MetricGAN

Implementation for paper "iMetricGAN: Intelligibility Enhancement for Speech-in-Noise using Generative Adversarial Network-based Metric Learning"

VCC2020-database

Attention_Backend_for_ASV

Attention Backend for Aotumatic Speaker Verification with Multiple Enrollment Utterances

TSNetVocoder

Capsule-Forensics

Old implementation and demonstration of the Capsule-Forensics. The Capsule-Forensics-v2 has been released here: https://github.com/nii-yamagishilab/capsule-forensics-v2

midi-to-audio

Project for MIDI to Audio Synthesis

vctk-silence-labels

NELE-GAN

Implementation for paper: Multi-Metric Optimization using Generative Adversarial Networks for Near-End Speech Intelligibility Enhancement

PartialSpoof

Jupyter Notebook

speaker_sex_attribute_privacy

Project for HIDING SPEAKER’S SEX IN SPEECH USING ZERO-EVIDENCE SPEAKER REPRESENTATION IN AN ANALYSIS/SYNTHESIS PIPELINE

SSL-SAS

Language independent SSL-based Speaker Anonymization system

ssnt-tts

An implementation of SSNT-TTS.

mla

A Multi-Level Attention Model for Evidence-Based Fact Checking

downloader-DR-VCTK-complete

downloader to obtain the complete DR-VCTK dataset (250GB)

Modular-CNN-for-CGIs-PIs-discrimination

ewc

fashion_adv

Fashion-Guided Adversarial Attack on Person Segmentation

partial_rank_similarity

Jupyter Notebook

VCC2020-listeningtest

xfever

Generalization_of_CMs_regularizations

The source code for the paper Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms (interspeech2023)