Center for Language & Speech Processing(CLSP), JHU Courses

Development and Deployment of Large-Scale AI Systems and Tasks They Still Struggle With

Explore the development and evaluation of large language models, focusing on data generation challenges, multi-model integration strategies, and areas where advanced AI systems still face significant limitations.

• YouTube
• 1 hour 9 minutes
• Self-Paced
• Free Video

Scalable Training for Machine Translation Made Successful for the First Time

Discover groundbreaking advances in machine translation training through a violation-fixing perceptron framework that enables scalable processing with 20M+ sparse features, achieving significant BLEU score improvements.

• YouTube
• 1 hour 4 minutes
• Self-Paced
• Free Video

Synthetic Dialogue Generation with Role-Playing LLMs II - Day 9 Afternoon

Explore advanced techniques for generating synthetic dialogues using role-playing LLMs, covering mechanistic interpretability, multi-agent configurations, and persona-based setups.

• YouTube
• 3 hours 58 minutes
• Self-Paced
• Free Video

Synthetic Dialogue Generation with Role-Playing LLMs II - Day 9 Afternoon

Explore advanced techniques for creating synthetic dialogues using role-playing large language models in this comprehensive tutorial continuation.

• YouTube
• 3 hours 58 minutes
• Self-Paced
• Free Video

Synthetic Dialogue Generation with Role-Playing LLMs - Day 9 Morning

Explore synthetic dialogue generation using role-playing LLMs and mechanistic interpretability techniques for advanced AI understanding and multi-agent configurations.

• YouTube
• 2 hours 58 minutes
• Self-Paced
• Free Video

Synthetic Dialogue Generation with Role-Playing LLMs I - Day 9

Explore synthetic dialogue generation techniques using role-playing large language models through comprehensive lecture slides from leading researchers.

• YouTube
• 2 hours 58 minutes
• Self-Paced
• Free Video

Speech Processing for Low Resource Scenarios with SpeechBrain II

Explore advanced speech processing techniques for low-resource languages using SpeechBrain in this comprehensive tutorial covering practical implementation strategies.

• YouTube
• 2 hours 7 minutes
• Self-Paced
• Free Video

Speech Processing for Low Resource Scenarios with SpeechBrain - Day 8 Afternoon

Dive into advanced speech processing techniques for low-resource languages using SpeechBrain in this hands-on lab session with expert Dr. Salima Mdhaffar.

• YouTube
• 2 hours 7 minutes
• Self-Paced
• Free Video

Speech Processing for Low Resource Scenarios I - Day 8 Morning

Explore speech semantic tasks and text-to-speech systems for low-resource languages with expert Dr. Salima Mdhaffar from Avignon University in this comprehensive tutorial session.

• YouTube
• 2 hours 26 minutes
• Self-Paced
• Free Video

Speech Processing for Low Resource Scenarios I - Day 8

Discover speech processing techniques for low-resource languages and scenarios through comprehensive slides covering fundamental approaches and methodologies.

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

Introduction to Multimodal Large Language Models II - Day 10 Afternoon

Explore advanced multimodal large language models through hands-on Python exercises, AF2/AF3 implementation, and MMAU-Pro training with expert researchers from UAM and UMD.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Introduction to Multimodal Large Language Models II - Day 10 Afternoon

Explore advanced multimodal large language models through expert slides covering practical implementations and cutting-edge techniques in this JSALT tutorial.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Introduction to Multimodal Large Language Models I - Day 10 Morning

Dive into multimodal large language models, covering LLM basics, transformers, CLIP/CLAP for images/audio, training methods, and audio language model development with practical applications.

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

Introduction to Multimodal Large Language Models I - Day 10 Morning

Discover how multimodal large language models integrate text, audio, and visual data through expert-led tutorial slides from leading researchers at JSALT 2025.

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

JSALT 2025 Summer Workshop - Opening Day: Speech and Language Technology Research Presentations

Explore cutting-edge speech and language technology research through opening presentations on multi-channel ASR, LLM role-playing agents, audio intelligence, and low-resource TTS systems.

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