Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official Code for Assem-VC @ICASSP2022
| Date | Stars |
|---|---|
| 2026-07-24 | 269 |
| 2026-07-25 | 269 |
| 2026-07-28 | 269 |
| 2026-07-30 | 269 |
| 2026-08-06 | 269 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Assem-VC — Official PyTorch Implementation  #### **Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques** Kang-wook Kim, Seung-won Park, Junhyeok Lee, Myun-chul Joe @ [MINDsLab Inc.](https://maum.ai/), SNU **Accepted to IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022** Paper: https://arxiv.org/abs/2104.00931 <br> Audio Samples: https://mindslab-ai.github.io/assem-vc/ <br> Update: Enjoy our pre-trained model with [Google Colab notebook](https://colab.research.google.com/drive/1rj0d2Xfl0s9TmtHSrJt-8J-eVT6eOgS5?usp=sharing)! Abstract: *In this paper, we pose the current state-of-the-art voice conversion (VC) systems as two-encoder-one-decoder models. After comparing these models, we combine the best features and propose Assem-VC, a new state-of-the-art any-to-many non-parallel VC system. This paper also introduces the GTA finetuning in VC, which significantly improves the quality and the speaker similarity of the outputs. Assem-VC outperforms the previous state-of-the-art approaches in both the naturalness and the speaker similarity on the VCTK dataset. As an objective result, the degree of speaker disentanglement of features such as phonetic posteriorgrams (PPG) is also explored. Our investigation indicates that many-to-many VC results are no longer distinct from human speech and similar quality can be achieved with any-to-many models.* ---  #### **Controllable and Interpretable Singing Voice Decomposition via Assem-VC** Kang-wook Kim, Junhyeok Lee @ [MINDsLab Inc.](https://maum.ai/), SNU **Accepted to NeurIPS Workshop on ML for Creativity and Design 2021 (Oral)** Paper: https://arxiv.org/abs/2110.12676 <br> Audio Samples: https://mindslab-ai.github.io/assem-vc/singer/ <br> Abstract: *We propose a singing decomposition system that encodes time-aligned linguistic content, pitch, and source speaker identity via Assem-VC. With decomposed speaker-independent information and the target speaker's embedding, we could synthesize the singing voice of the target speaker. In conclusion, we made a perfectly synced duet with the user's singing voice and the target singer's converted singing voice.* ## Requirements This repository was tested with following environment: - Python 3.6.8 - [PyTorch](https://pytorch.org/) 1.4.0 - [PyTorch Lightning](https://github.com/PytorchLightning/pytorch-lightning) 1.0.3 - The requirements are highlighted in [requirements.txt](./requirements.txt). ## Clone our Repository ```bash git clone --recursive https://github.com/mindslab-ai/assem-vc cd assem-vc ``` ## Datasets ### Preparing Data - To reproduce the results from our paper, you need to download: - LibriTTS train-clean-100 split [tar.gz link](http://www.openslr.org/resources/60/train-clean-100.tar.gz) - [VCTK dataset (Version 0.80)](https://datashare.ed.ac.uk/handle/10283/2651) - Unzip each files, and clone them in `datasets/`. - Resample them into 22.05kHz using `datasets/resample.py`. ```bash python datasets/resample.py ``` Note that `dataset/resample.py` was hard-coded to remove original wavfiles in `datasets/` and replace them into resampled wavfiles, and their filename `*.wav` will be transformed into `*-22k.wav`. - You can use `datasets/resample_delete.sh` instead of `datasets/resample.py`. It does the same role. ### Preparing Metadata Following a format from [NVIDIA/tacotron2](https://github.com/NVIDIA/tacotron2), the metadata should be formatted like: ``` path_to_wav|transcription|speaker_id path_to_wav|transcription|speaker_id ... ``` When you want to learn and inference using phoneme, the transcription should have only unstressed [ARPABET](https://en.wikipedia.org/wiki/ARPABET). Metadata containing ARPABET for LibriTTS train-clean-100 split and VCTK corpus are already prepared at `datasets/metadata`. If you wish to use custom data, you need to make the metadata
Excerpt of 15,466 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d6b5456d55906fe9, topic:deep-learning, topic:pytorch
matched fp:d6b5456d55906fe9, topic:speech-synthesis, readme:speech synthesis, readme:transcription