Divyesh Rajpura's repositories
pytorch-seq2seq
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText. [IN PROGRESS]
deep-clustering
A tensorflow implementation for Deep clustering: Discriminative embeddings for segmentation and separation
Deep-Speaker
Implementation of the paper "Deep Speaker: an End-to-End Neural Speaker Embedding System" available at https://arxiv.org/pdf/1705.02304.pdf"
deep-speaker-1
Deep Speaker: an End-to-End Neural Speaker Embedding System https://arxiv.org/pdf/1705.02304.pdf
ge2e-speaker-verification
Pytorch implementation of "Generalized End-to-End Loss for Speaker Verification"
kaldi
This is now the official location of the Kaldi project.
LSTM_PIT_Speech_Separation
Two-talker Speech Separation with LSTM/BLSTM by Permutation Invariant Training method.
PyTorch-Batch-Attention-Seq2seq
PyTorch implementation of batched bi-RNN encoder and attention-decoder.
PyTorch_Speaker_Verification
PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.
PyTorchZeroToAll
Simple PyTorch Tutorials Zero to ALL!
SpectralCluster
Python re-implementation of the spectral clustering algorithm in the paper "Speaker Diarization with LSTM"
sphereface_pytorch
A PyTorch Implementation of SphereFace.
Type-on-Strap
🎨 Simplistic, responsive jekyll based open source theme
voice-activity-detection
Voice Activity Detection (VAD) using deep learning. Student project in collaboration between s153077 and s134868 for the course 02456 Deep Learning at DTU. Supervised by Retune DSP.
zolan
Zolan is a minimal blog theme for Jekyll.