Singing Voice Synthesis based on Tacotron Architecture

 During my internship at Neosapience, one of the leading tech startups in speech synthesis field in Korea, I was assigned to develop a singing voice synthesis model.  In this project, I came up with an idea of adapting existing End-to-end TTS architecture (Tacotron) and manipulating it into singing voice synthesis system.   I took this approach because … Continue reading Singing Voice Synthesis based on Tacotron Architecture

Melodraw : A System for Melodic Contour Search from Embedded Space Using Line Drawings

 MeloDraw is an online application that automatically searches melody contours similar to user’s line drawing input. The input drawing is converted into a melodic contour based on predefined rules and the melodic contour is then passed to the melody proposal model as a query to find similar melodies. The model has a bi-directional RNN autoencoder … Continue reading Melodraw : A System for Melodic Contour Search from Embedded Space Using Line Drawings

Music Genre Classification Report

Introduction  The given task was  to use the deep learning techniques to solve music genre classification problem, which is one of major tasks in music information retrieval research. The task was to build and train a neural network model that accurately classifies the genres of songs from GTZAN dataset.  Since this competition was mainly focused … Continue reading Music Genre Classification Report

Instrument Classification Report

Introduction  The given task was to classify single-instrument recordings for ten instruments: Electronic Bass Guitar, Acoustic Brass, Acoustic flute, Acoustic Guitar, Acoustic Keyboard, Acoustic Mallet, Electronic Organ, Acoustic Reed, Acoustic String, and Acoustic Vocal. The goal of instrument identification is to make use of varying machine learning methodologies studied in our class. The input to … Continue reading Instrument Classification Report

Automatic music composition experiment

Automatic music composition experiment (2016) Scale-based melody and chord generation using charRNN Combined with some additional rule-based instrument arrangements Audio output rendering using Kontakt samples. Used Keras(Tensorflow) for neural network / Ruby on Rails for web / C++ for audio rendering Demo Video Implementation details Chord generation module Melodic curve generation module  Variational Autoencoder for … Continue reading Automatic music composition experiment

Create your website at WordPress.com
Get started