— IN-PERSON —
June 24-26, 2024
9:00-5:00 pm (MT) in-person meeting in Denver, Colorado
Instructor: Jeff Smith
Registration Deadline: June 20
Cost: $1,500
Course Description: Artificial Intelligence (AI) is changing the world in nearly unimaginable
ways. From deepfakes to ChatGPT, advances in synthetically generated media open new forms
of entertainment, art, and communication while creating new threat vectors for crime and
victimization. Forensic practitioners working with digital evidence need to understand the
threat of AI generated media by understanding how various techniques work, what their
limitations are, and what artifacts or forensic traces are left behind. This course will dig deeply
into understanding AI and its application in audio by exploring speech analysis and synthetic
voice generation. Attendees will learn the fundamentals of processing and generating audio
with Python by using open-source libraries and applications to set the stage for tasks such as
forensic audio analysis and authentication.
This course will take a hands-on approach to audio and is designed for all skill levels with no
previous Python experience needed. The course will cover the basics of Python programming,
audio processing, and synthesis. However, students should be familiar with the computer
command line (e.g., Mac Terminal, Windows Powershell).
*Please note that some of the methods and software discussed and presented may only be
available for demonstration purposes and/or to law enforcement agencies.
Course Outcomes:
Knowledge
Students will:
• Gain new perspectives to understand:
• How open-source software can be leveraged.
• Application techniques for Python.
• How Deep Learning AI is applicable to audio.
• Acquire knowledge that either enhances or is not covered in scientific literature.
Skills
Students will:
• Demonstrate a familiarity with Python and open-source repositories.
• Create AI-generated data that can be used in the lab for testing and evaluation.
Dispositions
Students will:
• Gain an appreciation for specific issues in forensic audio.
• Appreciate the need to understand new techniques capable of carrying out crime, fraud,
and victimization.
• Be able to critically evaluate different deep learning processes and algorithms.
• Enhance awareness of needs and opportunities in the field of forensic audio.
Course Schedule (Subject to Change):
Day 1: Python 101
− Environments and Notebooks
− Working with Data
− Processing Audio
Day 2: AI and Audio
− Speech Recognition
− Speaker Analysis
Day 3: AI-Generated Audio
− Synthetic Audio Generation
− Synthetic Voice Generation
Register Today
— IN-PERSON —
June 30-July 2, 2024
9:00 am-5:00 pm (MT) in-person meeting in Denver, Colorado
Instructor: Catalin Grigoras
Registration Deadline: June 20
Cost: $1,500
Course Description: Students will explore techniques to address challenges in the
authentication of digital audio with regard to evidence admissibility and counterfeit detection.
Foundations for forensic audio authentication, digital recording techniques, audio formats, and
time domain analyses will be discussed. Students will complete hands-on exercises using real
audio examples and forensic casework.
Previous experience/formal training with digital evidence is recommended.
*Please note that some of the methods and software discussed and presented may only be
available for demonstration purposes and/or to law enforcement agencies.
Course Outcomes:
Knowledge
Students will:
• Gain new perspectives to understand:
• The latest forensic audio authentication techniques.
• Advanced principles of forensic audio authentication.
• Forensic techniques, emerging science, and limitations of the forensic expert.
• Digital evidence seizure and acquisition.
• Acquire knowledge that either enhances or is not covered in scientific literature.
Skills
Students will:
• Take entrance and exit exams to gauge course’s effectiveness while informing student
regarding the advancement of their knowledge.
• Understand the questions that a forensic expert can answer.
• Know how to manipulate digital evidence and apply advanced techniques for forensic
audio authentication.
• Demonstrate a familiarity with general topics related to forensic audio.
Dispositions
Students will:
• Gain an appreciation for advanced issues in forensic audio.
• Be able to critically evaluate different forensic audio equipment, software, and
methods.
• Enhance awareness of needs and opportunities in the field of forensic audio.
Course Schedule:
1. Foundations for Forensic Audio Authentication
1.1. Digital Recording Techniques
1.2. WAV Format
1.3. Lossy Compression Formats
2. Theory, Demonstration, and Practice
2.1. Digital Evidence Seizure and Acquisition
2.1.1. Structure and Format Analysis
2.1.2. Time Domain Analysis
2.1.2.1. Zero Level Padding
2.1.2.2. Direct Current (DC)
2.1.2.3. Power
2.1.2.4. Butt-Splice Detection
2.1.2.5. Stereo Phase Analysis
2.1.3. Frequency Domain Analysis
2.2.3.1. Long Term Spectrum Analysis (LTAS)
2.2.3.2. Modified Discrete Cosine Transform (MDCT) Analysis
2.1.4. Other Analysis
2.2.4.1. Electric Network Frequency (ENF)
2.2.4.2. Copy-Insert (Clone) Detection
|
8:00 – 9:30 |
Registration + coffee |
|
9:30 – 10:00 |
Welcome and Introduction |
|
10:00 – 11:00 |
Invited Lecture 1: Miriam Iorwerth “The Present of Audio Education” |
|
11:15 – 12:00 |
Sound Bites & Coffee Moaning |
|
12:00 – 12:40 |
Papers 1 “Embedding Observation in Audio Education Software: A Preliminary Perspective” Kevin Garland
“Hybrid Teaching: AV Design Implementation for Music Lectures in Higher Education” Iker Ormazabal Martinez |
|
12:40 – 13:30 |
Lunch |
|
13:30 – 14:10 |
Papers 2 “Unveiling the Female Ear” Amandine Pras
“Audio, Acoustics, Wellbeing and the Environment” Ben Mosley |
|
14:15 – 15:15 |
Workshop 1 “Get Back: What Does Decolonised Audio Equipment, Education, and Research Purpose Look Like?” Amandine Pras, Kirk McNally, Kolawole Ganikale, Éliézer Oubda, Jude Brereton and Abdallah Ag Amano |
|
15:45 – 16:45 |
Workshop 2 “Embedding Sustainable Development in the Audio Curriculum” Ben Mosley |
|
17:00 – 18:00 |
Honorary Keynote: Jamie Angus-Whiteoak “Audio DSP Education: Keeping It Real” |
|
18:00 – … |
(Social Event) |
|
8:30 – 9:30 |
Registration + Coffee |
|
9:30 – 10:30 |
Keynote 2: Leslie Gaston-Bird “Immersive and Inclusive: Cracking the Credibility Code” |
|
10:30 – 11:30 |
Papers 3 (vocational theme) “The Music Technology Ensemble: An Approach to Implementing Problem-Based Learning for Newcomers in Audio Education” Anthony Marasco
“The L-Acoustics Program for Vocational Education in Loudspeaker System and Immersive Audio” Etienne Corteel
“Making Connections – A Work Experience Case Study” Patrick Quinn |
|
11:30 – 12:00 |
Coffee Break |
|
12:00 – 13:00 |
Papers 4 (critical listening) “Taxonomy of Critical Listening for Sound Engineers” Stephane Elmosnino
“FREQUIA – Development of an Adaptive, Personalized Technical Ear Training” Mark Bassett
“Trained Listeners Assessing the xHE-AAC Codec Performance for Streaming Audio-for-Video Broadcast” Christoph Thompson |
|
13:00 – 14:00 |
Lunch |
|
14:00 – 15:00 |
Workshop 3 “A Novel 3D Audio Teaching Tool for Analysis of Microphone Arrays” Mike Williams |
|
15:00 – 15:30 |
Coffee Break |
|
15:30 – 16:30 |
Workshop 4 “Issues and Strategies for Teaching Audio Mastering” Russ Hepworth-Sawyer |
|
17:00 – 18:00 |
Platinum Talk: Loop Earplugs |
|
18:00 – … |
(Social Event) |
|
9:30 – 10:00 |
Registration + Coffee |
|
10:00 – 11:00 |
Keynote 3: Gillian Desmarais “The Future of Audio Education in Primary and Secondary Public Schools” |
|
11:00 – 11:30 |
Sonic Networking: Finding Collaborators in HE |
|
11:30 – 12:00 |
Coffee Break |
|
12:00 – 13:00 |
Papers 5 (school education, diversity) “The STrOOM Framework: Using ICT in Schools to Foster Music Education in Elementary and Secondary Schools in Belgium” Frank Duchêne “De-fetishizing Audio Signals and Technologies in Bamako (Mali)” Emmanuelle Olivier “Educating the Educated: Challenges in Teaching Acoustics to Students With Existing Working Experience” Elena Prokofieva |
|
13:00 – 14:00 |
Lunch |
|
14:00 – 15:00 |
Workshop 5 “Do Musicians Need to Learn Music Software?” Rob Toulson, Mike Exarchos, Ryan Van Bibber and Gillian Desmarais |
|
15:00 – 15:30 |
Coffee Break |
|
15:30 – 16:30 |
Workshop 6 “Archives in Audio Education: From ‘I don’t care’ to ‘I am here'” Kirk McNally, Paul Thompson, Toby Seay and Nyssim Lefford |
|
16:30 – 17:00 |
Sound Reflections: Closing Remarks |
