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

A Feature-Based Model of Human Lexical Access - 2004

Explore a feature-based model of human lexical access, delving into the intricacies of language processing and speech recognition.

• YouTube
• 1 hour 13 minutes
• On-Demand
• Free Video

Towards Meaning: The Tectogrammatical Sentence Representation - 2001

Explore tectogrammatical sentence representation, a linguistic approach for analyzing sentence structure and meaning, presented by Jan Hajic in 2001.

• YouTube
• 1 hour 19 minutes
• On-Demand
• Free Video

Declarative Programming via a Relational Algebra - PhD Defense

Explore declarative programming through relational algebra in this PhD defense presentation, delving into advanced concepts and research findings.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

An Information State Approach to Collaborative Reference

Explore collaborative reference in dialogue systems using information state approaches. Gain insights into language processing and communication dynamics.

• YouTube
• 1 hour 28 minutes
• On-Demand
• Free Video

Acoustic Scene Analysis, Complex Modulations, and a New Form of Filtering - 2008

Explore acoustic scene analysis, complex modulations, and innovative filtering techniques for separating overlapping sound sources in noisy environments.

• YouTube
• 1 hour 18 minutes
• On-Demand
• Free Video

An Implementation of Sub-Space Model Based Automatic Speech Recognition - 2009

Explore advanced speech recognition techniques using sub-space models in this in-depth implementation guide from Johns Hopkins University's CLSP.

• YouTube
• 1 hour 21 minutes
• On-Demand
• Free Video

Recent Advances in Transition-Based Dependency Parsing - 2012

Explore recent developments in transition-based dependency parsing, including globally trained classifiers, non-projective tree coverage, and joint tagging and parsing models for improved accuracy and efficiency.

• YouTube
• 1 hour 7 minutes
• On-Demand
• Free Video

Probabilistic Linear Discriminant Analysis of i-Vector Posterior Distributions

Explore probabilistic linear discriminant analysis for i-vector posterior distributions in speaker recognition, enhancing understanding of advanced speech processing techniques.

• YouTube
• 37 minutes
• On-Demand
• Free Video

Automatic Information and Language Processing: Rethinking Evaluation

Explore groundbreaking insights on evaluating automatic information and language processing systems, challenging conventional approaches and proposing innovative methodologies.

• YouTube
• 1 hour 24 minutes
• On-Demand
• Free Video

Emerging Tech Governance: Opportunities and Challenges of AI in Medicine

Explore ethical challenges and governance gaps in emerging technologies like AI in medicine, genetic engineering, and consumer neurotechnology.

• YouTube
• 1 hour 12 minutes
• On-Demand
• Free Video

The Shoah Foundation's Archive: A 180 Terabyte Database for Teaching Tolerance

Explore a massive 180TB database of Holocaust survivor testimonies, learn about its creation, cataloging, and efforts to automate processes for wider educational use.

• YouTube
• 43 minutes
• On-Demand
• Free Video

The HAIRCUT System for Cross-Language Information Retrieval - 2013

Explore cross-language information retrieval with the HAIRCUT system, focusing on innovative techniques for multilingual search and retrieval.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

Automatic Speech Recognition - Lecture 2

Explore advanced concepts in automatic speech recognition, including acoustic modeling and feature extraction techniques.

• YouTube
• 1 hour 17 minutes
• On-Demand
• Free Video

An Overview and Challenges of Interactive HMI for Realizing Human-Like Interaction - 2024 JSALT

Explore interactive human-machine interfaces, their history, and recent advancements. Delve into HMI components, text-to-speech research, and future challenges in realizing human-like interactions.

• YouTube
• 1 hour 22 minutes
• On-Demand
• Free Video

Modeling Hierarchies of Sound for Audio Source Separation and Generation - 2024 JSALT

Explore hierarchical sound modeling for audio source separation and generation. Learn about extracting components, controlling models, detecting data memorization, and building interpretable controls.

• YouTube
• 1 hour 25 minutes
• On-Demand
• Free Video