A text-to-speech program using VAE on Mel spectrograms of phonemes.
-
Updated
Jun 3, 2020 - Python
A text-to-speech program using VAE on Mel spectrograms of phonemes.
This repository is to introduce the application of Activation Maximization for audio-domain data.
Music Genre Classification
Open Source Repository for the MASA Project
Simple neural net to classify the emotion in an audio
Different Signal Processing Tasks
MAIC VOICE AI 대회. 음성 멜-스펙트럼 데이터를 이용한 음성 질환 진단 및 분류.
Created an ASR (Automatic Speech Recognition) system that takes in individual recordings. Each recording represents a sentence composed of 5-10 English language digits, separated by adequate pauses. The system involves segmenting the sentence using a classifier, differentiating between background and foreground sounds.
2021-1 뇌인지공학 Term Project [👀🤜ing~ 06/24]
Introduction to Digital Signal Processing for Machine Learning
Embed chiptunes in 2D with Convolutional Auto Encoder and Mel Spectrograms
Speech emotion recognition models for the Moody web application.
This project was for the pattern recognition course I studied in college. This was the beginning of dealing with neural networks and 2 CNN models were made, 1-d model and 2-d model to deal with different forms of the data, audio and image, respectively.
Step onto the stage with Saxophone Hero, where your tenor saxophone is the key to unlocking a rhythmic adventure through a world of sheet music. In this game, your character scores points by hitting the right notes. Powered by machine learning, the game captures the pitch from your saxophone and translates it to player movement in real time.
Leveraged Dynamic Time Warping (DTW) to assess the similarity between specific audio tracks
Project to classify wav audio files using a CNN.
Acoustic Scene Classification System (DCASE2018 Task 1)
Overall process of speech signal processing (Mel-spectrogram & MFCCs) and loading data using Pytorch dataloader
This repository contains the code and methodology used for the BirdCLEF 2024 Kaggle competition, where I achieved a rank of 55th out of 974 participants, earning a bronze medal. The goal of this competition was to build a model that can accurately classify bird sounds.
Add a description, image, and links to the mel-spectrogram topic page so that developers can more easily learn about it.
To associate your repository with the mel-spectrogram topic, visit your repo's landing page and select "manage topics."