hmartelb

Héctor Martel's repositories

Pix2Pix-Timbre-Transfer

Musical Timbre Transfer using the Pix2Pix architecture

Language:PythonMIT117 5 3

avlit

Official source code of the INTERSPEECH 2023 paper: "Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model" (AVLIT)

Language:PythonMIT19 2 6

speech-denoising

Speech Denoising project for the Deep Learning course at Tsinghua University, spring 2021

Language:Jupyter NotebookMIT15 20

NSynth-MIDI-Renderer

Sample based concatenative synthesizer for the NSynth dataset. Render any MIDI (.mid) sequence with the notes of NSynth.

Language:PythonMIT10 2 2

meme-search

Search Engine for internet memes built for the final project of Web Information Retrieval at Tsinghua University, spring 2021.

Language:Jupyter NotebookMIT5 10

VideoSegmentation

Shot detection algorithm implementation in MATLAB. The aim is to detect the changes in scene by measuring degree of similarity between frames.

Language:MATLABMIT300

Collaborative 3D environment to compose music sequences built on top of Three.js and p5.js. Select drum kits and notes represented by 3D shapes, and have a chat with people in the same room. Everyone can add elements to the sequence!

Language:JavaScriptMIT200

AquaFX

Full-body interactive 3D Sound experience that recreates a swimming competition. Built on top of OpenFrameworks SDK for Kinect and PureData, using the OSC protocol to communicate between the two applications.

Language:C++200

GANs-for-artistic-style-transfer

Final project for the Machine Learning course at Tsinghua University, Fall 2020

Language:PythonMIT2 10

GenreRecognizer

Convolutional Neural Network for Music Genre Classification [Work in progress]

Language:PythonMIT200

TouchOSC-Sampler

PureData implementation of an audio sampler that can be controlled via OSC protocol. The user can interact using the TouchOSC app with the provided layout.

MIT200

DeepConvSep

Deep Convolutional Neural Networks for Musical Source Separation

Language:PythonGPL-3.0100

readme-template

README.md template for your open-source project

100

multimodal-video-captioning

Multimodal Video Captioning project for the Natural Language Processing course at Tsinghua University, spring 2021

Language:Jupyter NotebookMIT010

AIOps-Challenge

Language:Jupyter Notebook000

avlit-interspeech.github.io

Website containing audio samples for the INTERSPEECH 2023 paper: "Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model"

Language:HTMLMIT000