Name: Alef Iury
Type: User
Company: Universidade Federal de Goiás
Bio: Machine learning researcher and computer science undergraduate student focusing mostly on automatic speech recognition, sound event detection and bioacoustics.
Location: Goiânia, Goiás - Brasil
Alef Iury's Projects
This is an implementation in Pytorch of a Single Attention Convolutional Neural Network model for audio tagging and sound event detection.
This package aims at simplifying the download of the AudioSet dataset.
Implementation in Pytorch of Deep Learning models for Automatic Gender Recognition (AGR) for the paper: "A Comparison of Deep Learning Architectures for Automatic Gender Recognition from Audio Signals".
This repository has all the codes used in the work: classification of bees
Confidence interval computation for evaluation in machine learning using the bootstrapping approach
Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)
Download audioset data super fastly with youtube-dl, ffmpeg and python multiprocessing
Official implementation for the paper Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition
MARS5 speech model (TTS) from CAMB.AI
Unofficial PyTorch implementation of Few-Shot Keyword Spotting in Any Language. A model for few-shot keyword spotting in any language, trained with the Multilingual Spoken Words Corpus.
Code for the winning solution in the SE&R 2022 Challenge - SER track.
Code for the paper "Domain Specific Wav2vec 2.0 Fine-tuning For The SE&R 2022 Challenge"
This repository implements a Neuroevolution approach to the task of spontaneous speech emotion recognition using wav2vec2 embeddings and Natural Evolution Strategies.
Official implementation of INTERSPEECH 2021 paper 'Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings'
so-vits-svc fork with realtime support, improved interface and more features.
This is a web application developed in flask for quality evaluation of synthesized speech.
Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch