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

Visual Features for Context-Aware Speech Recognition - 2016

Explore visual features for context-aware speech recognition, improving transcription of consumer-generated multimedia content by adapting acoustic and language models to detected objects and scenes.

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

UCCA: A Computational Approach to Cross-Linguistic Semantic Representation

Explore UCCA, a cross-linguistic semantic representation approach. Learn about its scheme, parsing techniques, and applications in text-to-text generation tasks like machine translation and text simplification.

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

8-bit Methods for Efficient Deep Learning

Explore 8-bit methods for efficient deep learning, focusing on quantization techniques, optimizers, and inference for large language models to improve efficiency without performance loss.

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

Acquiring Big Mechanisms by Reading Primary Literature - 2015

Explore machine learning techniques for extracting causal models from scientific literature, focusing on Ras-driven cancers and systemic effects of interventions.

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

I-Vector Representation Based on GMM and DNN for Audio Classification - 2015

Explore I-vector approach for audio classification, including GMM mean modeling and recent subspace techniques. Learn about applications in language and dialect recognition using deep neural networks.

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

Extracting and Applying Measurements of Tongue Images - 2008

Explore tongue imaging techniques and their applications in speech production, motor control, and medical research. Gain insights into innovative approaches for studying vocal tract function.

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

Low-resource Morphological Generation with Neural Sequence-to-Sequence Models

Explore neural sequence-to-sequence approaches for morphological generation in low-resource languages, including multi-task learning, cross-lingual transfer, and semi-supervised techniques.

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

Foundational Models for Robotics: Removing the Engineer from the Loop

Explore foundational models in robotics, empowering users with AI capabilities and revolutionizing human-computer interfaces through autonomous systems and multi-modal properties.

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

Human Audition and Production in Speech Technology - 2009

Explore human audition and speech production mechanisms, their applications in speech technology, and implications for advancing speech processing systems.

• YouTube
• 1 hour 26 minutes
• On-Demand
• Free Video

Modeling Lexically Divergent Paraphrases in Twitter and Beyond - 2015

Explore innovative multi-instance learning models for capturing diverse paraphrases from Twitter data, and their applications in text-to-text generation and information extraction tasks.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Challenges and Advancements in Speaker Diarization and Recognition for Naturalistic Data

Explore advancements in speech technology for analyzing human interactions, focusing on child learning spaces and NASA APOLLO missions. Gain insights into ML-based audio processing and diarization techniques.

• YouTube
• 1 hour 1 minute
• On-Demand
• Free Video

Ethics and Data: Where Does the Twain Meet?

Explore the intersection of ethics and data in NLP, ML, and AI research, addressing inclusivity, fairness, and transparency while navigating IRB, copyright, and licensing issues.

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

Conlanging - The Art of Language Invention

Explore the art of constructed languages with David Peterson, creator of languages for Game of Thrones. Learn about naturalism in artistic language creation and its historical context.

• YouTube
• 1 hour 10 minutes
• On-Demand
• Free Video

Unsupervised Learning of Natural Language Structure - 2004

Explore unsupervised learning techniques for natural language structure, focusing on innovative syntactic representations that capture essential properties of language without labeled data.

• YouTube
• 1 hour 31 minutes
• On-Demand
• Free Video

Getting AI to Do Things I Can't: Scalable Oversight via Indirect Supervision

Explore AI-powered tools for pattern discovery in text and SQL labeling, enabling non-experts to achieve expert-level accuracy through indirect supervision and scalable oversight.

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