Name: Amirpasha Mobini Tehrani
Type: User
Company: Blausch Audio Co.
Bio: Multidisciplinary music technologist and machine learning eng. investigating the intersection of deep generative models and computer music.
Location: Berlin, Germany
Amirpasha Mobini Tehrani's Projects
Audio generation using diffusion models, in PyTorch.
Official PyTorch Implementation of CleanUNet (ICASSP 2022)
Noise supression using deep filtering
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder archi
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
Deeplearning.AI Generative Adversarial Networks (GANs) Specialization Solution
The official code repository for examples in the O'Reilly book 'Generative Deep Learning'
StyleGAN2 + MelGAN Audio Loop Generation
Official repo of ISMIR-21 publication, “A Benchmarking Initiative for Audio-domain Music Generation using the FreeSound Loop Dataset”.
GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis
MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms
Instructional notebooks on music information retrieval.
This is PyTorch Implementation of Neural Style Transfer Algorithm which is modified for Audios.
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
Real-time Neural Timbre Transfer
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
unofficial PyTorch implementation of 《REAL-TIME DENOISING AND DEREVERBERATION WTIH TINY RECURRENT U-NET》
Vector Quantization in Pytorch
Lavish audio synthesis from unfathomable variational abysses