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

Building Helpful Language Models - Challenges and Solutions

Explore challenges and solutions in aligning language models, including self-instruction, source tracing, and web interaction. Gain insights into building robust, transparent AI systems for practical applications.

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

Causes and Consequences of Word Structure - 2000

Explore word storage and access in speech perception and morphological productivity. Examine frequency effects on speech signals and lexicon structure, considering phonological patterns and lexical frequency.

• YouTube
• 1 hour 17 minutes
• Self-Paced
• Free Video

Quest for the Essence of Language - Multi-Tier Theory of Spoken Language

Explore a multi-tier theory of spoken language, examining utterances beyond words and phonemes to include syllables, features, and prosemes for more precise linguistic modeling.

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

Integrative Models of the Cardiac Ventricular Myocyte - 2005

Explore integrative modeling of cardiac ventricular myocytes, focusing on Ca2+-Induced Ca2+-Release mechanisms and their impact on heart function and disease. Gain insights into advanced cardiac electrophysiology research.

• YouTube
• 1 hour 11 minutes
• Self-Paced
• Free Video

Adapting Automatic Summarization to New Sources of Information - 2019

Explore adapting automatic summarization techniques for online narratives and cross-lingual content, focusing on challenges and solutions for non-traditional information sources.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video

Recent Advances of Deep Learning for Question Answering - 2016

Explore recent deep learning advancements in Question Answering, including improved representation learning and a novel two-way attention mechanism for natural language understanding.

• YouTube
• 1 hour 2 minutes
• Self-Paced
• Free Video

Retrieving Complex Answers through Knowledge Graph and Text

Explore techniques for retrieving complex answers by combining knowledge graphs and text. Learn about algorithms that identify relevant entities, relations, and supporting passages for comprehensive query responses.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video

Generative Agents: Interactive Simulacra of Human Behavior

Explore interactive simulations of human behavior using generative agents in a virtual village. Learn about memory streams, reflections, and planning for creating believable AI characters.

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

Language, Representation and Learning - 2001

Explore the intricate connections between language, mental representations, and cognitive development with insights from Barbara Landau's research in psycholinguistics and cognitive science.

• YouTube
• 1 hour 11 minutes
• Self-Paced
• Free Video

Multimodality, Context and Continuous Emotional Dynamics for Recognition

Explore computational approaches for multimodal emotion recognition, incorporating context and continuous dynamics. Learn about applications in healthcare, including facial expression analysis for autism research.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video

Improving Statistical Parsers Using Cross-Corpus Data - 2002

Enhance statistical parsing performance using cross-domain data and EM algorithm to infer missing information, leveraging partial constraints from other annotated corpora.

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

Speech, Language, and Machine Learning

Explore speech, language, and machine learning concepts with Jeff A. Bilmes from the University of Washington in this comprehensive lecture.

• YouTube
• 1 hour 11 minutes
• Self-Paced
• Free Video

When Will Computers Understand Shakespeare?

Explore computational challenges in understanding Shakespeare's 64th sonnet and potential solutions, examining progress in AI language comprehension.

• YouTube
• 1 hour 26 minutes
• Self-Paced
• Free Video

Embracing Language Diversity: Unsupervised Multilingual Learning - 2009

Explore unsupervised multilingual learning techniques for language analysis, including morphological segmentation, part-of-speech tagging, and parsing. Gain insights into cross-lingual patterns and their applications.

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

OUCH: Investigating Limitations of Hidden Markov Models in Speech Recognition

Explore speech recognition challenges, focusing on Hidden Markov Model limitations. Examine frame-to-frame independence assumptions and their implications for improving recognition accuracy.

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