College of Engineering and Polymer Science
Date of Last Revision
Number of Credits
Bachelor of Science in Computer Science
Date of Expected Graduation
Guitar transcription is a complex task requiring significant time, skill, and musical knowledge to achieve accurate results. Since most music is recorded and processed digitally, it would seem like many tools to digitally analyze and transcribe the audio would be available. However, the problem of automatic transcription presents many more difficulties than are initially evident. There are multiple ways to play a guitar, many diverse styles of playing, and every guitar sounds different. These problems become even more difficult considering the varying qualities of recordings and levels of background noise.
Machine learning has proven itself to be a flexible tool capable of generating accurate results in a variety of situations. To harness these benefits, a good program needs quality data and a model well suited for the task. The most promising models for automatic guitar transcription so far have been convolutional neural networks. These models are adequate, but they lack temporal context. A Liquid Time-constant Network is a type of recurrent neural network, and therefore it retains a temporal state. By combining these approaches, the resulting model should prove itself as a flexible tool adept to many situations and playing styles.
Michael L. Collard
Honors Faculty Advisor
Proprietary and/or Confidential Information
Hulet, Nathan, "Liquid Tab" (2023). Williams Honors College, Honors Research Projects. 1766.
Artificial Intelligence and Robotics Commons, Composition Commons, Computational Engineering Commons, Music Education Commons, Music Practice Commons, Music Theory Commons, Software Engineering Commons, Theory and Algorithms Commons