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

Computer Vision and Handwriting Recognition - Day 3 Afternoon

Explore computer vision fundamentals, neural network architectures, and handwritten text recognition systems with connections to speech recognition techniques.

• YouTube
• 3 hours 33 minutes
• Self-Paced
• Free Video

Computer Vision and Handwriting Recognition - Day 3 Afternoon

Explore computer vision techniques and handwriting recognition methods through comprehensive slides from Michal Hradiš's JSALT 2025 lecture at Johns Hopkins University.

• YouTube
• 3 hours 34 minutes
• Self-Paced
• Free Video

Speaker Diarization - From Modular to End-to-End Systems - Day 3 Morning

Discover speaker diarization techniques from traditional clustering methods to modern end-to-end neural systems that identify "who spoke when" in audio recordings.

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

Speaker Diarization - From Modular to End-to-End Systems - Day 3 Morning

Explore speaker diarization techniques from traditional modular approaches to modern end-to-end systems in this comprehensive technical presentation by Federico Landini.

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

Human Hearing and Speech Engineering - Day 2 Morning

Explore how human hearing properties evolved to shape speech and discover their implications for advancing speech technology engineering.

• YouTube
• 2 hours 42 minutes
• Self-Paced
• Free Video

Human Hearing and Speech Engineering - Day 2 Morning

Explore how human auditory perception principles inform modern speech processing and engineering applications through Hynek Hermansky's comprehensive lecture slides.

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

Robust Speech Recognition II - Day 7 Afternoon

Dive into advanced robust speech recognition techniques with expert slides covering cutting-edge methods for handling challenging acoustic conditions and improving system reliability.

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

Robust Speech Recognition II - Day 7 Afternoon

Master advanced target speaker ASR techniques with DiCoW method through hands-on lab sessions led by Brno University experts at JSALT 2025.

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

Robust Speech Recognition I - Day 7 Morning

Explore robust speech recognition challenges in real-world scenarios like meetings, covering noise, reverberation, multiple speakers, and technical solutions for conversational speech.

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

Robust Speech Recognition I - Day 7 Morning

Explore robust speech recognition techniques through expert slides from JSALT 2025, covering advanced methods for improving ASR system reliability and performance.

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

Speech Synthesis - From Models to Signals and Back - Day 6 Afternoon

Explore speech synthesis evolution from historical foundations to cutting-edge models and signal processing techniques with expert insights into current state-of-the-art methods.

• YouTube
• 3 hours 20 minutes
• Self-Paced
• Free Video

Speech Synthesis - From Models to Signals and Back - Day 6 Afternoon

Explore speech synthesis evolution from historical foundations to cutting-edge techniques and future innovations in this comprehensive technical presentation.

• YouTube
• 3 hours 20 minutes
• Self-Paced
• Free Video

Beyond Transformers - New Sequence Processing Architectures - Day 6 Morning

Explore cutting-edge sequence processing architectures that go beyond transformers, featuring insights from industry and academic experts on next-generation neural network designs.

• YouTube
• 3 hours 32 minutes
• Self-Paced
• Free Video

Beyond Transformers - New Sequence Processing Architectures - Day 6 Morning

Explore cutting-edge sequence processing architectures that go beyond transformers, featuring evolutionary algorithms for automated design of neural networks and AI systems.

• YouTube
• 3 hours 33 minutes
• Self-Paced
• Free Video

Unlocking Audio AI - Building a Massive Open Dataset for Instruction-Tuned Audio-Text Foundation Models

Discover how to build massive open audio-text datasets for instruction-tuned AI models, covering dataset creation, annotation techniques, and applications in transcription and voice assistants.

• YouTube
• 1 hour 24 minutes
• Self-Paced
• Free Video