myusernameisstudy Goto Github PK

audio-and-acoustics-signal-processing-speech-enhancement-project

Audio and Acoustics Signal Processing: Speech Enhancement Project

audio-snr

Mixing an audio file with a noise file at any Signal-to-Noise Ratio (SNR)

audio-super-res

Audio super resolution using neural networks

audio-super-resolution

audio-visual-speech-enhancement

audio_classification_using_lstm

Classification of Urban Sound Audio Dataset using LSTM-based model.

audio_sr

Hierarchical RNN with Perceptual Loss for Audio Super-Resolution

audion

Audio Super Resolution through Deep Learning

audiosuperresolution

Generate higher quality audio from a lower one, using Convolutional neural network.

automatic_speech_recognition

End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

bach-audio-super-resolution

Bach:The learning based model for audio super resolution

cnn-for-single-channel-speech-enhancement

Convolutional neural nets for single channel speech enhancement

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.

cs230-project

CS230 Final Project - Audio Super Resolution

deep-learning-developer-course-projects

dnp

Audio Denoising with Deep Network Priors

enhancement-coded-speech

keras-unet-vocal-separation

lstm_for_bss

Blind source separation of audio signals using LSTM

mir_eval

Evaluation functions for music/audio information retrieval/signal processing algorithms.

multimodal-vae-public

A PyTorch implementation of "Multimodal Generative Models for Scalable Weakly-Supervised Learning" (https://arxiv.org/abs/1802.05335)

speechdenoisingdnn

Removing various types of noises present in the speech using Deep Neural Networks

t-lstm

Time-Aware LSTM

tfmusicaudioencoder

An Autoencoder for WAV files

wave-u-net-for-speech-enhancement

Improved speech enhancement with the Wave-U-Net, a deep convolutional neural network architecture for audio source separation, implemented for the task of speech enhancement in the time-domain.