AI for Music and Audio

(4-Week Course)

author.full_name

Authored by Carlos Arana

|

Course Code: OLMSC-100

Next semester
starts June 24

4 Weeks

Level 1

Level 1

1-Credit Tuition

$515

Understanding the many ways you can use artificial intelligence (AI) to help you in your creative process can take you to the next level in many different industries, including music. With this quickly evolving technology we’re already seeing creative and innovative approaches to music analysis, production, and composition.

The essential mission of this course is to, as much as possible, lift the veil and demystify the AI models and tools. The goal is to teach you about the current models and apps in the market, their utility and scope. Furthermore, the course incorporates sections on the underlying technologies, so that you can be prepared and trained to receive, interact with, control, and benefit from the tools, apps, and plug-ins that will undoubtedly be developed and introduced to the market at a rapid pace in the coming years.

Read More

In this course, you’ll delve into the core principles of AI and its diverse applications in music and audio. Through hands-on activities, you’ll gain experience with AI models and algorithms and have the opportunity to explore the range of AI-based apps and software available in the market.

This course is designed to integrate the use of AI on the different stages of a musical work lifecycle. You’ll start by coming to an understanding of musical content for AI. First, you’ll learn about the fundamentals of AI models and architectures, and related terminology. Then, we move to examining how musical content is represented for then being processed by AI models/architectures. For that, we delve into the basics of Signal Processing and Music Information Retrieval (MIR), which is crucial for understanding the nuances of musical content.

Then we’ll focus on practical applications as you work on extracting and recognizing musical content through AI. This encompasses rhythm detection, melody extraction, chord detection, and source separation, exploring both the theoretical framework and practical apps used for these tasks.

In the next stage, we’ll explore processing musical content using AI, and discover all of the ways in which AI is applied to music production, mixing, and mastering. You’ll learn about technological advancements in AI that have enhanced music production tasks and the practical application of these techniques using industry-leading AI tools and commercial apps. We’ll also get into AI's transformative potential in the distribution and consumption of musical works. We’ll examine AI’s impact on processes like genre classification, music recommendation, playlist creation, and audio identification.

The final stage focuses on creating musical content with AI. You’ll delve into generative AI, covering the evolution, principles, and applications of AI in music composition. You’ll learn about various neural network architectures, and their role in creating original musical content, as well as the most used apps in the market for music generation. This lesson not only teaches the technical aspects of generative AI but also addresses the legal and ethical challenges in AI-generated music.

We will wrap up the course by presenting and analyzing different alternatives and creative workflows, utilizing a variety of tools and apps discussed in the course, with its distinct types and functionalities. This includes focusing on the features of each tool and app for specific parts of the composition and/or arrangement process, ensuring a comprehensive understanding of how these technologies can enhance musical creativity.

No coding or programming experience is needed for this course. You’ll be provided with Python code and libraries for understanding the behind-the-scenes procedures used in AI models and apps.

This course will encourage you to experiment with AI technologies at key stages of a musical work lifecycle, from creation to production and consumption, which will allow you to increase the productivity of your work, stimulate creativity, and enhance your musical projects.

By the end of the course, you will be able to:

  • Describe the fundamental concepts of AI and the various types of models used for tasks in music analysis and processing.
  • Discuss the technological background behind AI techniques, such as source and vocal separation, melody extraction, chord recognition, and implement them using available apps and software in the market.
  • Grasp the fundamental principles and practical skills required for AI-driven music production, particularly in intelligent mixing and mastering, while exploring the transformative impact of these innovations on music production workflows.
  • Identify the key components and AI-based technologies behind song feature extraction, genre classification, recommendation, and personalization systems, recognizing their pivotal role in enhancing music listening experiences.
  • Evaluate diverse generative AI neural network architectures used in music composition, including their strengths and weaknesses.
  • Describe the different techniques used by GenAI models to assist the composition and songwriting processes.
  • Gain practical proficiency in leveraging commercial AI tools and apps to enhance creative music composition processes and workflows.
  • Develop a critical mindset for assessing the effectiveness, usefulness, and quality of apps and software used for various applications of AI in music and audio.
  • Discuss the complexities and copyright challenges associated with the authorship of GenAI musical works and the training of the deep learning models backing these apps.
Read Less
Overview Syllabus Requirements Instructors
Request Info

Syllabus

Lesson 1: Artificial Intelligence Types and Fundamentals of Signal Processing and Music Information Retrieval

  • Introduction to Artificial Intelligence (AI)
  • Introduction to Machine Learning (ML)
  • Introduction to Deep Learning (DL) and Neural Networks
  • Introduction to Generative AI (GenAI)
  • Understanding Sound and Music through Signal Processing
  • Why Music Analysis Matters in the Digital World: Music Information Retrieval (MIR)
  • Assignment 1: Understanding Musical Content for AI

Lesson 2: Audio Content Analysis and Source Separation

  • Comprehensive Techniques for Music Analysis
  • Pulse, Beat and Tempo Detection
  • Voice and Melody Extraction
  • Polyphony and Source Separation
  • Key and Chord Recognition
  • Assignment 2: Recovering Musical Content through AI

Lesson 3: Music Production and Distribution Using AI

  • Introduction to AI-Driven Music Production
  • Analysis and Classification of Musical Genres
  • AI Automatic Mixing
  • AI in Automated Mastering
  • Audio Enhancement and Restoration
  • Music Recommendation and Personalization
  • Assignment 3: Processing Musical Content Using AI

Lesson 4: Generative AI in Music

  • Rule-Based/Statistical Generative Techniques vs. Deep Learning AI Models
  • Neural Network Architectures in Deep Music Generation
  • Multimodal GenAI Models: Text to Music and Image to Music
  • Singing Voice Synthesis
  • Practical Applications and Future Directions in AI Music Generation
  • Human-AI Collaboration: Levels of Control in GenAI Music Apps
  • Copyright: Who Owns a Song Created Using Generative AI Models?
  • Assignment 4: Creating Musical Content with AI

Requirements

Prerequisites and Course-Specific Requirements 

Prerequisite Courses, Knowledge, and/or Skills
Students should have:

  • a basic, working knowledge of music production, including working with a DAW. 
  • a basic, working knowledge of songwriting (song characteristics, genre, groove and mood; what a drum pattern is, the difference between melody and accompaniment, and what a chord progression is).
  • a curious mindset and the desire to critically think how AI will influence and enhance many aspects of music related activities and the music industry as a whole.

Software

  • Full-featured Digital Audio Workstation (DAW), such as Pro Tools (Studio or Ultimate), Logic Pro, Cubase Pro, Ableton Live (Suite or Standard), Reaper, Reason, or FL Studio (Producer or Signature). Note that GarageBand is not acceptable.
  • Moises premium license
  • iZotope Neutron 4 (Elements edition acceptable)
  • Each of the following generative AI application types are required:
    • Text-to-MIDI, such as AIVA subscription (Standard or Pro)
    • Text-to-music, such as Stable Audio (free)
    • Style transfer, such as Musicfy (free)
    • Large language model-based chatbot, such as ChatGPT 3.5 (free)
  • Magenta Studio (free)
  • Each of the following programming related applications (installation will be covered within the course):

Hardware

  • One of the following studio monitoring options (both recommended):
    • Studio monitors (pair), such as JBL 305Ps or better, as well as an audio interface and necessary cables
    • Over-ear studio headphones, such as Sennheiser HD 600, Sony MDR-7506, Philips SHP9500, Audio-Technica ATH-M50x, etc.
  • Recommended: MIDI controller

Student Deals
After enrolling, be sure to check out our Student Deals page for various offers on software, hardware, and more. Please contact support@online.berklee.edu with any questions.


General Course Requirements

Below are the minimum requirements to access the course environment and participate in Live Classes. Please make sure to also check the Prerequisites and Course-Specific Requirements section above, and ensure your computer meets or exceeds the minimum system requirements for all software needed for your course. 

Mac Users

PC Users

All Users

  • Latest version of Google Chrome
  • Zoom meeting software
  • Webcam
  • Speakers or headphones
  • External or internal microphone
  • Broadband Internet connection

Instructors

Carlos Arana

Author & Instructor

Carlos “Charly” Arana is a guitarist, producer, and researcher. His specialties range from Latin American rhythms to the application of machine learning and artificial intelligence techniques for music. As a guitarist, arranger, and musical director he has worked and recorded with artists from all over the world, including legendary Bossa Nova singer Maria Creuza, whose band he was a member of. He has edited a number of books for Hal Leonard and Warner Bros. Publications (Alfred Publications), and for his studies and research on machine learning and AI he has been invited as a speaker in congresses and seminars at some of the most prestigious technology universities, such as MIT and UC Berkeley.

Questions?

Contact our Academic Advisors by phone at 1-866-BERKLEE (U.S.), 1-617-747-2146 (INT'L), or by email at advisors@online.berklee.edu.

Get Info
Call
Text