Audio Visual Courses

Royal Holloway, University of London;  VocalEyes

Creating Audio Description: Equality, Diversity, and Inclusion

Explore how to design and create audio descriptions and audio introductions that fully represent a film, play, or TV programme.

• FutureLearn
• 4 weeks, 3 hours a week
• On-Demand
• Free Online Course (Audit)

Teacher's Tech

How to Transform Excel Data into a Striking Visual Report with Microsoft Power BI

Transform Excel data into interactive visual reports using Microsoft Power BI. Learn importing, data manipulation, DAX expressions, chart creation, and report customization in this beginner-friendly tutorial.

• YouTube
• 30 minutes
• On-Demand
• Free Video

Proko

Drawing from Imagination - Tips on Improving Visual Memory

Discover techniques to enhance visual memory, observation skills, and creativity through engaging drawing exercises and games for improved imagination-based artwork.

• YouTube
• 1 hour 20 minutes
• On-Demand
• Free Video

The Power of Audio: A Conversation with Tim Ferriss

The Power of Audio: A Conversation with Tim Ferriss with Chase Jarvis, Tim Ferriss

• CreativeLive
• 57 minutes
• On-Demand
• Free Online Course

The Power of Visual Storytelling

The Power of Visual Storytelling with Cheriss May, Kenna Klosterman

• CreativeLive
• 1 hour 4 minutes
• On-Demand
• Free Online Course

Elevating Voices of Women + Non-Binary Visual Storytellers

Elevating Voices of Women + Non-Binary Visual Storytellers with Daniella Zalcman, Kenna Klosterman

• CreativeLive
• 1 hour
• On-Demand
• Free Online Course

Visual Poetry

Visual Poetry with Noémie Marguerite, Kenna Klosterman

• CreativeLive
• On-Demand
• Free Online Course

Strange Loop Conference

Equitable Experiential Access - Audio Description

Exploring audio description as a tool for equitable access, focusing on user-centered design and innovative approaches to create inclusive auditory experiences for diverse audiences.

• YouTube
• 39 minutes
• On-Demand
• Conference Talk

Alan Turing Institute

Visual and Spatial Digital Humanities Research for Japanese Culture

Explore visual and spatial digital humanities research for Japanese culture, focusing on innovative projects using computer vision, machine learning, and geographic information science to analyze historical data.

• YouTube
• 35 minutes
• On-Demand
• Free Video

Valerio Velardo - The Sound of AI

Audio Processing in Keras with Kapre

Learn to process audio in Keras using Kapre, exploring its advantages, features, and implementation. Discover how to embed audio transformations within deep learning models for optimized GPU-based calculations and easier deployment.

• YouTube
• 28 minutes
• On-Demand
• Free Video

Valerio Velardo - The Sound of AI

How to Implement Audio Data Augmentation in Python

Implement audio data augmentation techniques in Python, including noise addition, time stretching, pitch scaling, polarity inversion, and random gain, with practical code examples.

• YouTube
• 21 minutes
• On-Demand
• Free Video

Valerio Velardo - The Sound of AI

Batch Preprocess Audio Datasets in 1 Command

Explore praudio, a Python library for efficient audio dataset preprocessing. Learn its design, implementation, and usage for streamlining complex audio processing tasks in AI projects.

• YouTube
• 21 minutes
• On-Demand
• Free Video

Valerio Velardo - The Sound of AI

Pre-Processing Audio with Different Durations

Learn to preprocess audio data with varying lengths using PyTorch and torchaudio. Master techniques for cutting and zero-padding waveforms to standardize input for machine learning models.

• YouTube
• 21 minutes
• On-Demand
• Free Video

Valerio Velardo - The Sound of AI

Automatic Song Remixes With Audio Signal Processing and Simple Machine Learning

Explore Python-based Infinite Remixer for automatic song remixes using beat tracking and Nearest Neighbours search. Learn system design, usage, experiments, and potential improvements for innovative music creation.

• YouTube
• 30 minutes
• On-Demand
• Free Video

Valerio Velardo - The Sound of AI

Preprocessing Audio Datasets for Machine Learning

Build an audio preprocessing pipeline for AI in Python, covering STFT, zero-padding, and min-max normalization. Learn to batch process audio files efficiently for machine learning applications.

• YouTube
• 59 minutes
• On-Demand
• Free Video