Rpersie's repositories
espnet
End-to-End Speech Processing Toolkit
cwavegan
Conditional WaveGAN: Generating audio samples conditioned on class labels
Automatic-Music-Transcription
Automatic music transcription performed on jazz solos in the presence of noise using TDNN acoustic model, HMM language model
Tensorflow-MultiGPU-VAE-GAN
A single jupyter notebook multi gpu VAE-GAN example with latent space algebra and receptive field visualizations.
tensorflow-generative-model-collections
Collection of generative models in Tensorflow
pykaldi
A Python wrapper for Kaldi
uPIT-for-speech-separation
Speech separation with utterance-level PIT experiments
xdecoder
Fast, portable, enhanced ASR decoder
pix2pix
Tensorflow implementation of pix2pix(cGAN) for audio source separation
rsrgan
Robust Speech Recognition Using Generative Adversarial Networks (GAN)
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.
Singing_Voice_Separation_RNN
Singing-Voice Separation From Monaural Recordings Using Deep Recurrent Neural Networks
generative_model_speech
Phone generation model/VAE/GAN/VAE+GAN
Multi-channel-speech-extraction-using-DNN
A tensorflow implementation of my paper Combining beamforming and deep neural networks for multi-channel speech extraction
Listen-Attend-and-Spell-Pytorch
Listen Attend and Spell (LAS) implement in pytorch
Cross-Domain-CWS
Code for IJCAI 2018 paper "Neural Networks Incorporating Unlabeled and Partially-labeled Data for Cross-domain Chinese Word Segmentation"
aes-lac-2018
Pytorch code of "A new automatic speech recognizer for Brazilian Portuguese based on deep neural networks and transfer learning" submitted to AES-LAC 2018
cublasHgemm-P100
Code for testing the native float16 matrix multiplication performance on Tesla P100 and V100 GPU based on cublasHgemm
music-source-separation
Separating singing voice from music based on deep neural networks in Tensorflow
PyTorch-GAN
PyTorch implementations of Generative Adversarial Networks.
speech-denoising-wavenet
A neural network for end-to-end speech denoising
CycleGAN
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
SeGAN
SeGAN: Segmenting and Generating the Invisible (https://arxiv.org/pdf/1703.10239.pdf)
CGMM-MVDR
Implement of CGMM-MVDR beamforming
nn_mask
multichannel linear filters based on mask estimation neural networks for CHiME4
Speech_Enhancement_MMSE-STSA
A statistical model-based Speech Enhancement Using MMSE-STSA
Weikun-Zhengshuang
over-the-air_speech_recogniztion_attack