Ajili M's repositories
asvspoof2017
an implement of asvspoof 2017 using pytorch
atom-gpp-compiler
An atom package that allows you to compile and run C++ and C within the editor.
Automatic_Speech_Recognition
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
DeadSimpleSpeechRecognizer
CNN based Minimal model for recognizing word
DeepSpeech
A PaddlePaddle implementation of DeepSpeech2 architecture for ASR.
DeepSpeech-1
A TensorFlow implementation of Baidu's DeepSpeech architecture
forced-alignment-tools
A collection of links and notes on forced alignment tools
google_keyword_detection_challenge
https://www.kaggle.com/c/tensorflow-speech-recognition-challenge/
kaldi-gstreamer-server
Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
kaldi-readers-for-tensorflow
readers that enable reading kaldi ark in tensorflow
MixedEmotions
Documentation for the MixedEmotions Toolbox
Model-Compression-Papers
Papers for deep neural network compression and acceleration
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_MLP_for_ASR
This code implements a basic MLP for speech recognition. The MLP is trained with pytorch, while feature extraction, alignments, and decoding are performed with Kaldi. The current implementation supports dropout and batch normalization. An example for phoneme recognition using the standard TIMIT dataset is provided.
replayed_distillation
Implementation of Data-free Knowledge Distillation for Deep Neural Networks (on arxiv!)
smart_home
One-shot learning
Spoken-language-identification-1
Spoken language identification with deep learning
voice-vector
A deep neural network for finding text-independent speaker embedding written in tensorflow and tensorpack
voxceleb-ivector
Voxceleb1 i-vector based speaker recognition system
voxceleb-luigi
Luigi pipeline to download VoxCeleb(2) audio from YouTube and extract speaker segments