Pinned Repositories
Artificial-Intelligence-with-Python
Code repository for Artificial Intelligence with Python, published by Packt
aubio
a library for audio and music analysis
ConvolutionaNeuralNetworksToEnhanceCodedSpeech
In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves speech quality (PESQ) by up to 0.25 MOS-LQO points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec (AMR-WB). In a subjective CCR listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to G.711, even en par with uncoded speech.
DL
dlnith
DeepLearning@NITH
exploratory_computing_with_python
Getting-Started-with-Modern-Python
Code repository for Getting Started with Modern Python, Published by Packt
intro_programming
A set of IPython notebooks and learning resources for an Introduction to Programming class, focusing on Python.
my_attempts
numpy_exercises
Numpy exercises. Thanks @Kyubyong! This would be an amazing set of exercises for our freshers to learn from!
phildani7's Repositories
phildani7/ConvolutionaNeuralNetworksToEnhanceCodedSpeech
In this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves speech quality (PESQ) by up to 0.25 MOS-LQO points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec (AMR-WB). In a subjective CCR listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to G.711, even en par with uncoded speech.
phildani7/intro_programming
A set of IPython notebooks and learning resources for an Introduction to Programming class, focusing on Python.
phildani7/Z
This repository contains a Matlab class, a Python module, a Jupyter notebook, and a Julia module which implement/illustrate several methods/functions for audio signal processing.
phildani7/AIDL_KB
A Knowledge Base for the FB Group Artificial Intelligence and Deep Learning (AIDL)
phildani7/awesome-python-scientific-audio
Curated list of python software and packages related to scientific research in audio
phildani7/Deep-Learning-models
Implementation of basic deep learning models using tensorflow and keras
phildani7/Deep-Learning-with-Keras
Code repository for Deep Learning with Keras published by Packt
phildani7/DeepSpeech
A TensorFlow implementation of Baidu's DeepSpeech architecture
phildani7/dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
phildani7/gluon-nlp
NLP made easy
phildani7/hw
RTL, Cmodel, and testbench for NVDLA
phildani7/Image-compression-and-video-coding
phildani7/Keras-Classification-Models
Collection of Keras models used for classification
phildani7/keras-neural-alu
A Keras implementation of Neural Arithmatic and Logical Unit
phildani7/Keras-RetinaNet-for-Open-Images-Challenge-2018
Code for 15th place in Kaggle Google AI Open Images - Object Detection Track
phildani7/Mastering-Natural-Language-Processing-with-Python-Video
Mastering Natural Language Processing with Python by Packt Publishing
phildani7/ml-suite
Getting Started with Xilinx ML Suite
phildani7/NALU
Basic pytorch implementation of NAC/NALU from Neural Arithmetic Logic Units paper by trask et.al
phildani7/NALU-1
Keras Implementation of: "Neural Arithmetic Logic Units", Trask et al., ArXiV, 2018
phildani7/NALU-for-division
phildani7/NALU-Keras
A keras implementation of [Neural Arithmetic Logic Units](https://arxiv.org/pdf/1808.00508.pdf) by Andrew et. al.
phildani7/NALU-pytorch
A PyTorch Implementation of "Neural Arithmetic Logic Units"
phildani7/nalu_implementation
This repository is created to show the Neural Arithmetic Logic Unit implementation in python using Tensorflow. The code in this repo complements my article on Medium on NALU
phildani7/python-fundamentals
Introductory Python Series for UC Berkeley's D-Lab
phildani7/pywt
PyWavelets - Wavelet Transforms in Python
phildani7/stanford-cs-229-machine-learning
VIP cheatsheets for Stanford's CS 229 Machine Learning
phildani7/TrustScore
To Trust Or Not To Trust A Classifier. A measure of uncertainty for any trained (possibly black-box) classifier which is more effective than the classifier's own implied confidence (e.g. softmax probability for a neural network).
phildani7/Verilog-Generator-of-Neural-Net-Digit-Detector-for-FPGA
Verilog Generator of Neural Net Digit Detector for FPGA
phildani7/vp_awsfpga
Virtual Platform for AWS FPGA support
phildani7/web-audio-recognition