Institute of Art Design + Technology
Dún Laoghaire
On Show
 Courses
Search
Close
3D Animation 3D Design Modelmaking + Digital Art Animation Applied Psychology Art Character MakeUp Design Costume Design Creative Computing Creative Music Production Cyberpsychology Design for Change Film + Television Production Interaction + User Experience Design New Media Studies Photography Production Design User Experience Design Visual Communication Design




Kittitat Bamrung 

BSc [Hons] Creative Computing

Hello! My name is Kittitat Bamrung. I am a final-year Creative Computing student with a passion for programming, drawing, and learning guitar! These passions are the main reason I have chosen to combine what I love doing into this final-year Thesis. The accumulated knowledge gained through my time at IADT has provided me with wide-ranging experiences in various technologies and skills such as Front-end Development, Back-end Development, Artificial Intelligence, UX/UI, and Critical Thinking. I am now very keen to apply these experiences to real-world applications.

This video will take you through the brief run down of the application and the overview of the architecture. The project overview has also been supplied in the attachments section.
The Homepage of the application features the backbone of the operation, where the audio can be easily drag and drops into the input field to transcribe the audio! The option to separate the guitar track from the mixture that may contains other instruments such as basses, drums, vocals, pianos etc.
The Tab Visualiser page handles the main functionality of the application. As the name suggests, it lets the user visualise the output of the guitar transcription model with the ability to playback the audio via MIDI synth and seek to the desired section.
The Login page allows the user to login, where additional features could be access for the logged-in users such as the functionality to favourite the tab for later practices, and the tab editor to allows users to correct any misplacement caused by the prediction.
The Tab Editor page allows the logged-in user to edit any notes and create new notes but not delete note as this feature could not be implement in time.
The Upload page shares major similarities with the Favourite and Songs pages. Each page would return the list of songs from the database that the user either uploaded or favourited. While the Songs page displays all of the songs that has been uploaded by all users.
Tablature - Automatic Guitar Tablature

The application is a platform for guitarists and music students to have a place to directly practice songs and/or replicate songs without the need to create the guitar track entirely from scratch. The app allows a variety of features to fulfil the mentioned requirements such as the option to separate guitar audio from its mixture for prediction, the ability to favourite songs for later practices, copy the song for editing, and listen to the predicted tablature via the MIDI player.


Download Thesis PDF Download Thesis Overview PDF

Automatic Guitar Transcription For Educational Purposes

Most of the tablature accessible online today were available for popular songs and artists. However, advancements in artificial intelligence has present new opportunities to create a way to enable musicians to quickly transcribe guitar tablature and encourage a wider audience to pick up guitar. This research will explore the possibility of using artificial intelligence to tackle the music information problem of audio classification model. It will comprehensively conclude the research, design, and development of the mentioned application.


Download Thesis PDF Download Thesis Overview PDF
Creative Computing
Top