Syllabus

LEARNING OUTCOMES

Students will learn recent deep learning & artificial intelligence (AI) models and network architectures for audio, work on course exercises and start building AI applications for their own purposes. Students will also learn and practice preparing data sets and traning deep learning models using cluster network in Aalto University. Further, students will gain an understanding of the differences in input, computational cost and sonic characteristics between the different models, which will help formulate a course project. 

Credits: 5

Schedule: 19.04.2022 - 06.05.2022

Teacher in charge (valid for whole curriculum period):

Teacher in charge (applies in this implementation): Koray Tahiroglu

Contact information for the course (applies in this implementation):

CEFR level (valid for whole curriculum period):

Language of instruction and studies (applies in this implementation):

Teaching language: English. Languages of study attainment: English

CONTENT, ASSESSMENT AND WORKLOAD

Content

• valid for whole curriculum period:

  In Deep Learning with Audio, we will introduce students to the state of the art in deep learning models for sound and music generation, giving an overview of recent artificial intelligence (AI) implementations such as WaveNet, WaveGAN, Google Magenta (NSynth, GANSynth, Melody RNN...) and audio style transfer. There will be hands-on exercises on each course topic. We will provide code templates that integrate the functionality from open source deep learning audio projects, such as Google's Magenta, into Pure Data programming environment. We will also provide detailed setup instructions and automated scripts to make installation of the required tools as easy as possible (for Pure Data, Python, Conda, Magenta, PyExt). Students will further explore a particular model and incorporate it into their own project work.

Assessment Methods and Criteria

• valid for whole curriculum period:

  The course consists of lectures, exercises, reading materials, tutoring individual or group works. Students will submit their documented project work and ~ 750 words learning diary, both grounds the course examination and final grade. Each student project work will be assessed with the following criteria: Design Values, Aesthetics and Originality; UI design and Production Values; Code Design Quality; Project Analysis - Depth of Understanding; Idea generation and implementation; and Presentation style.

Workload

• valid for whole curriculum period:

  This course is a project-based course. In addition to 36h of contact teaching, at the end of the course, students will submit and present their projects. 

   

DETAILS

Study Material

• valid for whole curriculum period:

  https://github.com/SopiMlab/DeepLearningWithAudio

Substitutes for Courses

• valid for whole curriculum period:

  Substitutes for Courses

Prerequisites

• valid for whole curriculum period:

  Prerequisites

FURTHER INFORMATION

Further Information

• valid for whole curriculum period:

  Keywords:

  Deep learning with Audio, artificial intelligence (AI), digital musical interactions, new musical instruments, generative adversarial networks (GANs), Pure Data, Python, Google Magenta, new interfaces for musical expression

  Teaching Period:

  2020-2021 Spring V

  2021-2022 Spring V

  Course Homepage: https://mycourses.aalto.fi/course/search.php?search=DOM-E5132

  Registration for Courses: Sisu replaces Oodi on 9 August, 2021. Priority order to courses is according to the order of priority decided by the Academic committee for School of Arts, Design and Architecture: https://www.aalto.fi/en/services/registering-to-courses-and-the-order-of-priority-in-aalto-arts

  sign-up through Weboodi, latest 1 week before the first day of the course

   

  The order of priority for admitting students to courses at Aalto ARTS 1.1.2018 onwards (approved by The Committee of Arts, Design and Architecture on 10.10.2017)

  The order of priority is as follows:

  1. students for whom the course is compulsory for their major/programme and who have scheduled it for the current academic year in their personal study plan (HOPS);
  2. exchange students for whom the course is a part of his/her officially approved learning agreement and scheduled to be taken during the current semester;
  3. students for whom the course is compulsory for their major/programme and who have not completed it yet;
  4. students, for whom the course is part of his/her major s or programme s alternative studies and has been scheduled in the student's PSP (HOPS) for the current academic year
  5. students, for whom the course is part of his/her major s or programme s alternative studies and who have not completed the requisite number of credits for alternative studies yet;
  6. students for whom the course is compulsory for their minor;
  7. students, for whom the course is part of his/her minor subject s alternative studies and who have not completed the requisite number of credits for alternative studies yet;
  8. students who have applied for the course through a student mobility scheme (internal mobility within Aalto University, flexible study right (JOO) studies etc.);
  9. other students.

   

  Courses that are intended to be multidisciplinary (e.g. UWAS courses) may apply an order of priority based on the learning outcomes of the course, while bearing in mind the university obligation of enabling students to complete their degrees within the normative duration of study set for the degree. The order of priority does not apply to courses organised by the Centre for General Studies or doctoral courses.

  This decision on the order of priority does not influence the right of the teacher to define prerequisites for the course.

   

Description