Valerio Velardo - The Sound of AI Courses

How to Conduct Literature Review Effectively

2 reviews

Learn effective literature review techniques, from selecting relevant papers to organizing references. Gain insights on note-taking, resource selection, and summarizing findings for successful research.

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

Intensity, Loudness, and Timbre

1 review

Explore sound power, intensity, loudness, and timbre, covering key concepts like amplitude envelope, harmonic content, and modulation. Gain insights into audio signal processing for machine learning.

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

Custom Audio PyTorch Dataset with Torchaudio

1 review

Learn to create a custom audio dataset using PyTorch and torchaudio, focusing on the UrbanSound8K dataset. Explore basic I/O functions in torchaudio and implement essential dataset class methods.

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

AI, Machine Learning and Deep Learning

1 review

Explore AI, machine learning, and deep learning concepts, including supervised, unsupervised, and reinforcement learning paradigms. Learn when to use traditional ML or deep neural networks for audio applications.

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

How to Extract Audio Features

Explore acoustic feature extraction from audio signals, covering time and frequency domains, spectral leakage, windowing, frames, and hop length for enhanced audio processing understanding.

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

Types of Audio Features for Machine Learning

Explore audio feature types for ML: time, frequency, and time-frequency domains. Learn categorization based on abstraction, ML approach, and temporal scope for intelligent audio applications.

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

Understanding Audio Signals for Machine Learning

Explore audio digital signals, analog-to-digital conversion, and key concepts like sampling, quantization, and aliasing for machine learning applications.

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

Sound and Waveforms

Explore the physics of sound, waveform analysis, and key concepts like frequency and pitch. Gain insights into periodic and aperiodic sounds, phase, and the relationship between pitch and frequency.

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

This AI Recognises Moods in Songs and Explains How It Does It

Explore a deep learning architecture for recognizing and explaining moods in songs, focusing on mid-level features, datasets, and potential applications in music emotion analysis.

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

What Are the Business Use Cases of AI Music Generation?

Explore AI music generation's business applications, from functional music to interactive songs, and understand their potential implementation timeline in the coming years.

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

Generating Melodies with a Neural Network

Explore neural network-based melody generation using LSTM, from data preparation to sampling with temperature, in this hands-on tutorial for AI music enthusiasts.

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

Training a Long-Short Term Memory Network for Melody Generation

Build and train an LSTM network for generating folk melodies using Tensorflow and Keras. Learn preprocessing, model architecture, training sequences, and testing the final model.

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

How to Create Melody Sequences to Train a Neural Network

Generate melody sequences for RNN-LSTM training: learn to create time series data, map songs to lists, and prepare inputs using one-hot encoding for neural network-based melody generation.

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

Preprocessing Song Dataset for Melody Generation

Collate encoded songs, create integer mapping for symbolic notation, and prepare data for neural network ingestion in melody generation preprocessing.

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

Preprocessing Song Dataset for Melody Generation - Pt. 2

Explore encoding songs as time series for LSTM-based melody generation, focusing on data representation techniques for effective neural network input.

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