Speech & Audio Courses and Certifications

Stanford Seminar - Audio Research: Transformers for Applications in Audio, Speech and Music

A research seminar on using Transformer architectures for raw audio synthesis, large-scale audio understanding, and discrete latent representations.

• YouTube
• 48 minutes
• Self-Paced
• Free Online Course

AI for Audio and Music

Use AI across audio workflows: vocal cleanup, stem separation, mastering support, sound design, speech recognition, text-to-speech, and AI-assisted composition.

• Coursera
• 9 weeks, 1 hour a week
• Self-Paced
• Paid Course

Cloud Speech API: 3 Ways

Learn three ways to build speech and language solutions with pre-trained Google Cloud APIs.

• Google Skills
• 1 hour
• Self-Paced
• Paid Course

Neural Network Applications: Audio Processing: Wolfram U

Build an audio classifier in Wolfram Language: encode audio data, apply convolutional and recurrent networks, perform network surgery on pretrained models, and demonstrate transfer learning.

• Wolfram U
• 1 hour
• Self-Paced
• Free Online Course

Process and Translate Speech with Azure AI Speech Services

Process and Translate Speech with Azure Cognitive Speech Services

• Microsoft Learn
• 1 hour 45 minutes
• Self-Paced
• Free Online Course

Valerio Velardo - The Sound of AI

Preprocessing Audio Datasets for Machine Learning

Build a Python audio preprocessing pipeline that batches files, extracts log spectrograms, pads data, and normalizes features for AI applications.

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

HuggingFace

XLS-R: Large-Scale Cross-Lingual Speech Representation Learning on 128 Languages

A research talk on XLS-R’s self-supervised cross-lingual speech representations, trained on 128 languages and applied to recognition, translation, and classification.

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

Aleksa Gordić - The AI Epiphany

AudioGen- Textually Guided Audio Generation - Paper Explained

A deep dive into AudioGen, a text-guided audio synthesis model, covering its representations, losses, architecture, and results.

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

Improving Customer Experiences with Speech-to-Text and Text-to-Speech - AI Show

See how speech recognition and speech synthesis improve customer experiences through transcription, multilingual voices, and custom neural voice demonstrations.

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

Multi-Modal Systems with the OpenAI API

489 ratings at DataCamp

Develop Multi-Modal Applications with the OpenAI APITo build applications that are accessible to as wide an audience as possible, it's important that they can accept inputs in different modalities, like text and speech.

• DataCamp
• 2 hours
• Self-Paced
• Free Trial Available

Sam Witteveen

Gemini TTS - Native Audio Out: Using Text-to-Speech for Speech and Dialogue

1 rating

Explore Gemini TTS capabilities for speech generation, including single speaker and multi-speaker podcast demos, with practical examples in Google AI Studio and Colab.

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

Spoken Language Processing in Python

285 ratings at DataCamp

Learn Speech Recognition and Spoken Language Processing in Python We learn to speak far before we learn to read.

• DataCamp
• 4 hours
• Self-Paced
• Free Trial Available

Multi-Modal Models with Hugging Face

181 ratings at DataCamp

Harness the Power of Multi-Modal AIDive into the cutting-edge world of multi-modal AI models, where text, images, and speech combine to create powerful applications.

• DataCamp
• 4 hours
• Self-Paced
• Free Trial Available

Communicating with Natural Language

Learn voice user interface techniques that turn speech into text and vice versa. Build a speech recognition model using deep neural networks.

• Udacity
• 16 hours
• Self-Paced
• Paid Course

Eran Feit

Audio Classification with Transformers - Speech Commands Recognition and Real-Time Speech-to-Text

Master audio classification with Wav2Vec2 transformers to build a real-time speech command recognition system that identifies spoken words like "up," "down," "left," and "right."

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