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

Context-Sensitivity and Stochastic Unification-Based Grammars

Explore context-sensitive interactions in probabilistic grammars, log-linear models, and stochastic unification-based grammars with implications for optimality theory.

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

Acoustic Event Detection at Amazon Alexa

Explore acoustic event detection for AI systems, focusing on Alexa Guard's development and research to improve AED model accuracy and efficiency.

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

Listener-oriented Phonology - 2004

Explore listener-oriented phonology, focusing on French vowel-initial words and Optimality Theory. Learn how this approach handles complex phonological processes and improves constraint formulation.

• YouTube
• 1 hour 20 minutes
• Self-Paced
• Free Video

BitFunnel: How Bing Uses Bloom Filters for Search

Explore BitFunnel algorithm powering Bing search, using Bloom filters to efficiently process queries and search billions of documents, challenging conventional wisdom in text indexing.

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

New Methods to Capture and Exploit Multiscale Speech Dynamics - 2007

Explore new methods for capturing and exploiting multiscale speech dynamics, including formant estimation and adaptive short-time Fourier analysis for speech enhancement.

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

OCP-Place, Similarity, and Multiplicative Interaction in Linguistics - 2008

Explore OCP-Place constraint in linguistics, examining its universality and variation across languages using natural classes similarity metric and multiplicative constraint interaction models.

• YouTube
• 1 hour 16 minutes
• Self-Paced
• Free Video

Machine Translation - 2009

Learn statistical machine translation techniques, including alignment models, phrase-based systems, and decoding algorithms. Explore cutting-edge approaches to improve translation quality.

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

Adversarial Machine Learning: Beyond Manipulating Pixels and Words

Explore vulnerabilities in sequential machine learning and challenge assumptions about imperceptible attacks on image classification through human behavioral studies.

• YouTube
• 1 hour 6 minutes
• Self-Paced
• Free Video

Modeling Common Ground for Multimodal Communication - 2018

Explore multimodal communication in human-machine interactions using a 3D simulation platform. Learn about VoxML modeling language for encoding objects and actions in shared task environments.

• YouTube
• 1 hour 15 minutes
• Self-Paced
• Free Video

A Bayesian View of Inductive Learning in Humans and Machines - 2004

Explore how humans make successful generalizations from limited evidence through Bayesian inferences constrained by implicit domain theories, with applications to machine learning.

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

Combining AI and Crowd for Professional-Quality Translation at Scale

Explore how Unbabel combines AI and crowdsourcing to deliver fast, high-quality translations at scale, breaking down language barriers between companies and customers.

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

Reducing Confusions and Ambiguities in Speech Translation - 2005

Explore techniques to enhance speech translation by addressing accent-related confusions, named entity recognition, and semantics-based disambiguation for improved accuracy and understanding.

• YouTube
• 1 hour 12 minutes
• Self-Paced
• Free Video

New Twists for New Tricks - Making Audio Deep Learning Practical

Explore innovative approaches to audio deep learning, addressing practical challenges in efficiency, unsupervised learning, and resource-limited scenarios for enhanced audio processing and source separation.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Connecting Vision and Language End-to-End - 2018

Explore neural models for vision-language understanding, focusing on End-to-End Module Networks and dense video captioning. Learn about interpretable, compositional approaches to visual question answering.

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

Modelling Human Syntax by Means of Probabilistic Dependency Grammars - 2007

Explore probabilistic dependency grammars for modeling human syntax, addressing linguistic phenomena beyond context-free grammars and discussing generative models and parsing algorithms.

• YouTube
• 1 hour 18 minutes
• Self-Paced
• Free Video