sas91 Goto Github PK

academic-kickstart

Easily create a beautiful website using Academic and Hugo

cocktail

dc_integration

Tight integration of spatial and spectral features for BSS with Deep Clustering embeddings

eb1a

EB1A Full Application - I-140 and I-485

espnet

End-to-End Speech Processing Toolkit

feature-extraction-for-speech-recognition

Python Implementation of the Feature Extraction Process in Kaldi

jhu-neural-wpe

Neural Dereverberation

kaldi

This is now the official location of the Kaldi project.

nara_wpe

Different implementations of "Weighted Prediction Error" for speech dereverberation

nn-gev

Neural network supported GEV beamformer

pb_chime5

Speech enhancement system for the CHiME-5 dinner party scenario

pykaldi2

Yet another speech toolkit based on Kaldi and PyTorch

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.

pytorch_complex

A temporal module for PyTorch-ComplexTensor

rir-generator

Room Impulse Response Generator

s3prl

Self-Supervised Speech Pre-training and Representation Learning Toolkit.

sas91.github.io

sednn

deep learning based speech enhancement using keras python, make it easy to use

sentence-completion

MSR sentence completion challenge implementation (RNNLM, LSA total similarity, word2vec total similarity) in Python

shinjiwlab.github.io

sms_wsj

SMS-WSJ: Spatialized Multi-Speaker Wall Street Journal database for multi-channel source separation and recognition

torchain

WIP: pytorch FFI wrapper for Kaldi chain loss (a.k.a. Lattice Free MMI)

vat_chainer

Implementation of Virtual adversarial training with chainer