marco_atlanta's Projects
Implementation of the paper "Attentive Statistics Pooling for Deep Speaker Embedding" in Pytorch
Boosting Self-Supervised Embeddings for Speech Enhancement
Conditional Diffusion Probabilistic Model for Speech Enhancement
PyTorch implementation of Representation Learning with Contrastive Predictive Coding by Van den Oord et al. (2018)
Keras implementation of Representation Learning with Contrastive Predictive Coding
Contrastive Predictive Coding for Automatic Speaker Verification
Code for DCASE 2020 task 1a and task 1b.
Phase-aware speech enchancement with Deep Complex U-Net
Diffusion Model 4 Speech Enhancement
This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.
Implementation of Fisher's Linear Discriminant (LDA)
hippo-base
Bayesian low-rank adaptation for large language models
Documenting my journey into ML/AI
Multi-label MFoM Framework for Speech Articulatory Attributes Detection
Open Data from TULIP Lab
Perceptual Contrast Stretching on Target Feature for Speech Enhancement (Accepted by INTERSPEECH 2022)
(NOT Official) Implementation DC-UNet (ICLR 2019)
Library for training machine learning models with privacy for training data
Projects. And then some.
A PyTorch implementation of Legendre Memory Units (LMUs) and it's FFT variant
Neural Turing Machines (NTM) - PyTorch Implementation
Code for paper "Large Language Models are Efficient Learners of Noise-Robust Speech Recognition"
deep learning based speech enhancement using keras or pytorch, make it easy to use
A PyTorch-based Speech Toolkit
Jun and Huck's Tensor-Train Network Toolbox
An STFT/iSTFT for PyTorch.