This is your work, valued

Songxiang Liu

Elite
@liusongxiang

Omni & Multimodal LLM & SLM

liusongxiang.github.io

StarGAN-Voice-Conversion. This is a pytorch implementation of the paper: StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks

523

Large-Audio-Models. Keep track of big models in audio domain, including speech, singing, music etc.

514

ppg-vc. PPG-Based Voice Conversion

349

efficient_tts. Pytorch implementation of "Efficienttts: an efficient and high-quality text-to-speech architecture"

116

diffsvc. DiffSVC demo page

81

BNE-Seq2SeqMoL-VC. Demo for "Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling"

7

speaker-verification-d-vector. Implementation of state of the art d-vector approach for speaker verification

7

end2endAC. Audio samples for the paper "End-to-end Accent Conversion"

5

AcademiCodec. AcademiCodec: An Open Source Audio Codec Model for Academic Research

2

StyleTransferVC. Audio samples for the paper "Transferring Source Style in Non-Parallel Voice Conversion"

2

ebook. Organize valuable books

1

End-to-end-ASR-Pytorch. This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

1

WaveGrad. Implementation of Google Brain's WaveGrad high-fidelity vocoder (paper: https://arxiv.org/pdf/2009.00713.pdf). First implementation on GitHub.

1

WaveRNN-Pytorch. Fatcord's Alternative WaveRNN (Faster training)

1

piano-synthesis. Code accompanying ML4MD ICML 2020 paper - "Generative Modelling for Controllable Audio Synthesis of Expressive Piano Performance".

1

bigvsan. Pytorch implementation of BigVSAN

1

nonparaSeq2seqVC_code. Implementation code of non-parallel sequence-to-sequence VC

1

liusongxiang.

1

Unsupervised_HMM. Shell

1

Cpp-Primer-5th-Note-CN. 《C++ Primer中文版（第5版）》笔记

1

ASR_course. ASR course at Chula 2018

1

pytorch-kaldi. pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

1

WFST-decoder-for-phoneme-posterior. Shell

1