Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features

Overview

MediumVC

MediumVC is an utterance-level method towards any-to-any VC. Before that, we propose SingleVC to perform A2O tasks(Xi → Ŷi) , Xi means utterance i spoken by X). The Ŷi are considered as SSIF. To build SingleVC, we employ a novel data augment strategy: pitch-shifted and duration-remained(PSDR) to produce paired asymmetrical training data. Then, based on pre-trained SingleVC, MediumVC performs an asymmetrical reconstruction task(Ŷi → X̂i). Due to the asymmetrical reconstruction mode, MediumVC achieves more efficient feature decoupling and fusion. Experiments demonstrate MediumVC performs strong robustness for unseen speakers across multiple public datasets. Here is the official implementation of the paper, MediumVC.

The following are the overall model architecture.

Model architecture

For the audio samples, please refer to our demo page. The more converted speeches can be found in "Demo/ConvertedSpeeches/".

Envs

You can install the dependencies with

pip install -r requirements.txt

Speaker Encoder

Dvector is a robust speaker verification (SV) system pre-trained on VoxCeleb1 using GE2E loss, and it produces 256-dim speaker embedding. In our evaluation on multiple datasets(VCTK with 30000 pairs, Librispeech with 30000 pairs and VCC2020 with 10000 pairs), the equal error rates(EERs)and thresholds(THRs) are recorded in Table. Then Dvector with THRs is also employed to calculate SV accuracy(ACC) of pairs produced by MediumVC and other contrast methods for objective evaluation. The more details can access paper.

Dataset VCTK LibriSpeech VCC2020
EER(%)/THR 7.71/0.462 7.95/0.337 1.06/0.432

Vocoder

The HiFi-GAN vocoder is employed to convert log mel-spectrograms to waveforms. The model is trained on universal datasets with 13.93M parameters. Through our evaluation, it can synthesize 22.05 kHz high-fidelity speeches over 4.0 MOS, even in cross-language or noisy environments.

Infer

You can download the pretrained model, and then edit "Any2Any/infer/infer_config.yaml".Test Samples could be organized as "wav22050/$figure$/*.wav".

python Any2Any/infer/infer.py

Train from scratch

Preprocessing

The corpus should be organized as "VCTK22050/$figure$/*.wav", and then edit the config file "Any2Any/pre_feature/preprocess_config.yaml".The output "spk_emb_mel_label.pkl" will be used for training.

python Any2Any/pre_feature/figure_spkemb_mel.py

Training

Please edit the paths of pretrained hifi-model,wav2mel,dvector,SingleVC in config file "Any2Any/config.yaml" at first.

python Any2Any/solver.py
Owner
谷下雨
美中不足
谷下雨
L-SpEx: Localized Target Speaker Extraction

L-SpEx: Localized Target Speaker Extraction The data configuration and simulation of L-SpEx. The code scripts will be released in the future. Data Gen

Meng Ge 20 Jan 02, 2023
A simple python script to play bell sound in your system infinitely, just for fun and experimental purposes

A simple python script to play bell sound in your system infinitely, just for fun and experimental purposes

نافع الهلالي 1 Oct 29, 2021
Spotipy - Player de música simples em Python

Spotipy Player de música simples em Python, utilizando a biblioteca Pysimplegui para a interface gráfica. Este tocador é bastante simples em si, mas p

Adelino Almeida 4 Feb 28, 2022
XA Music Player - Telegram Music Bot

XA Music Player Requirements 📝 FFmpeg (Latest) NodeJS nodesource.com (NodeJS 17+) Python (3.10+) PyTgCalls (Lastest) MongoDB (3.12.1) 2nd Telegram Ac

RexAshh 3 Jun 30, 2022
Make an audio file (really) long-winded

longwind Make an audio file (really) long-winded Daily repetitions are an illusion anyway.

Vincent Lostanlen 2 Sep 12, 2022
Analysis of voices based on the Mel-frequency band

Speaker_partition_module Analysis of voices based on the Mel-frequency band. Goal: Identification of voices speaking (diarization) and calculation of

1 Feb 06, 2022
❤️ This Is The EzilaXMusicPlayer Advaced Repo 🎵

Telegram EzilaXMusicPlayer Bot 🎵 A bot that can play music on telegram group's voice Chat ❤️ Requirements 📝 FFmpeg NodeJS nodesource.com Python 3.7+

Sadew Jayasekara 11 Nov 12, 2022
Python CD-DA ripper preferring accuracy over speed

Whipper Whipper is a Python 3 (3.6+) CD-DA ripper based on the morituri project (CDDA ripper for *nix systems aiming for accuracy over speed). It star

671 Jan 04, 2023
A python program for visualizing MIDI files, and displaying them in a spiral layout

SpiralMusic_python A python program for visualizing MIDI files, and displaying them in a spiral layout For a hardware version using Teensy & LED displ

Gavin 6 Nov 23, 2022
Noinoi music is smoothly playing music on voice chat of telegram.

NOINOI MUSIC BOT ✨ Features Music & Video stream support MultiChat support Playlist & Queue support Skip, Pause, Resume, Stop feature Music & Video do

2 Feb 13, 2022
Play any song directly into your group voice chat.

Telegram VCPlayer Bot Play any song directly into your group voice chat. Official Bot : VCPlayerBot | Discussion Group : VoiceChat Music Player Suppor

Shubham Kumar 50 Nov 21, 2022
Music generation using ml / dl

Data analysis Document here the project: deep_music Description: Project Description Data Source: Type of analysis: Please document the project the be

0 Jul 03, 2022
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Project DeepSpeech DeepSpeech is an open-source Speech-To-Text engine, using a model trained by machine learning techniques based on Baidu's Deep Spee

Mozilla 20.8k Jan 03, 2023
Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features

MediumVC MediumVC is an utterance-level method towards any-to-any VC. Before that, we propose SingleVC to perform A2O tasks(Xi → Ŷi) , Xi means utter

谷下雨 47 Dec 25, 2022
A python package for calculating the PESQ.

PyPESQ (WIP) Pypesq is a python wrapper for the PESQ score calculation C routine. It only can be used in evaluation purpose. INSTALL pip install https

Jingdong Li 269 Dec 18, 2022
Codes for "Efficient Long-Range Attention Network for Image Super-resolution"

ELAN Codes for "Efficient Long-Range Attention Network for Image Super-resolution", arxiv link. Dependencies & Installation Please refer to the follow

xindong zhang 124 Dec 22, 2022
Audio2midi - Automatic Audio-to-symbolic Arrangement

Automatic Audio-to-symbolic Arrangement This is the repository of the project "Audio-to-symbolic Arrangement via Cross-modal Music Representation Lear

Ziyu Wang 24 Dec 05, 2022
A python script that can play .mp3 URLs upon the ringing or motion detection of a Ring doorbell. The sound plays through Sonos speakers.

Ring x Sonos A python script that plays .mp3 files whenever a doorbell is rung or a doorbell detects motion. Features Music! Authors @braden Running T

braden 0 Nov 12, 2021
Audio augmentations library for PyTorch for audio in the time-domain

Audio augmentations library for PyTorch for audio in the time-domain, with support for stochastic data augmentations as used often in self-supervised / contrastive learning.

Janne 166 Jan 08, 2023
An audio guide for destroying oracles in Destiny's Vault of Glass raid

prophet An audio guide for destroying oracles in Destiny's Vault of Glass raid. This project allows you to make any encounter with oracles without hav

24 Sep 15, 2022