Valerio Velardo - The Sound of AI Courses

How to Conduct Literature Review Effectively

8 ratings

Learn a practical workflow for selecting relevant research, reading papers, taking notes, organizing references, and summarizing literature review findings.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Custom Audio PyTorch Dataset with Torchaudio

1 rating

Build a custom PyTorch audio dataset with torchaudio by implementing data loading, sample paths, labels, and dataset methods for UrbanSound8K.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Intensity, Loudness, and Timbre

1 rating

Explore how sound intensity, loudness, and timbre arise from power, envelopes, harmonics, and modulation.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

Music Theory Concepts for Melody Generation

1 rating

Learn music theory fundamentals and encode melodies as time-series data for training neural networks to generate music.

• YouTube
• 39 minutes
• Self-Paced
• Free Video

Limitations and Future Vision of Generative Music AI

1 rating

Explore limitations of generative music AI, including deep learning challenges, music representation issues, and research procedures. Discover potential solutions and future directions in this field.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

AI, Machine Learning and Deep Learning

1 rating

A high-level guide to distinguishing AI, machine learning, and deep learning, with guidance on choosing traditional ML or deep neural networks for audio.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Text-to-Speech and Voice Cloning Course - Demystifying TTS and Voice Cloning

Uncover how AI generates speech through TTS and voice cloning, exploring zero-shot techniques, speaker embeddings, quality tradeoffs, and ethical considerations in 40 minutes.

• YouTube
• 40 minutes
• Self-Paced
• Free Video

Text-to-Speech and Voice Cloning Course - How Machines Process Text

Explore how TTS systems transform raw text into speech-ready phonemes, covering normalization, grapheme-to-phoneme conversion, and solving ambiguity challenges in AI speech synthesis.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Text-to-Speech and Voice Cloning Course - Neural TTS Revolution

Explore how deep learning revolutionized text-to-speech with WaveNet and Tacotron breakthroughs, neural vocoders, and modern voice cloning architectures like VALL-E.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Formant Synthesis, Concatenative Synthesis and Statistical Methods for Text-to-Speech

Explore traditional text-to-speech methods including formant synthesis, concatenative synthesis, and HMM-based approaches that preceded neural networks in speech generation.

• YouTube
• 45 minutes
• Self-Paced
• Free Video

Generative Music AI Course

Master AI-powered music creation through generative techniques, from Markov chains to transformers, targeting both technologists and musicians seeking creative applications.

• YouTube
• 11 hours 37 minutes
• Self-Paced
• Free Video

Uncle Bob SOLID Principles for ML Engineers

Master SOLID principles to write cleaner, more maintainable machine learning code with practical examples and real-world applications for ML engineers.

• YouTube
• 1 hour 16 minutes
• Self-Paced
• Free Video

PyTorch for Audio and Music Processing

Master PyTorch and torchaudio for deep learning in audio and music processing, including neural networks, mel spectrograms, CNNs, and GPU-accelerated sound classification.

• YouTube
• 2 hours 55 minutes
• Self-Paced
• Free Video

Audio Signal Processing for Machine Learning

Master audio signal processing fundamentals and extract features from raw audio data using Python to build powerful AI applications with hands-on implementation techniques.

• YouTube
• 10 hours 24 minutes
• Self-Paced
• Free Video

Melody Generation with RNN-LSTM

Master melody generation using Long Short-Term Memory networks to create AI-composed music from preprocessing datasets to converting neural network outputs into MIDI files.

• YouTube
• 4 hours 56 minutes
• Self-Paced
• Free Video