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

Student Lightning Talks: Text Generation, Reward Consistency, and Evaluation Validity

Explore cutting-edge research on text generation models, reward consistency in RLHF, and validity of compositional generalization evaluations through student presentations at JHU's CLSP.

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

Probabilistic Models of Relational Domains

Explore probabilistic models for relational domains with Stanford's Daphne Koller, covering advanced techniques for representing and reasoning about complex, interconnected data structures.

• YouTube
• 1 hour 28 minutes
• Self-Paced
• Free Video

Prominence in Conversational Speech: Pitch Accent, Contrast and Givenness

Explore pitch accent, contrast, and givenness in conversational speech. Discover how these factors impact prominence patterns and their role in improving text-to-speech synthesis naturalness.

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

Bipartite Graph Factorization in Static Decoding Graphs with Long-Span Acoustic Context

Explore bipartite graph factorization for efficient speech recognition search space representation, addressing challenges in large vocabulary systems with long-span acoustic context.

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

Foundation Models and the Transfer of Embodied Autonomy

Explore challenges in developing foundation models for sequential decision-making, including transfer learning, and discuss future research directions in embodied autonomy.

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

An Overview of Digital Libraries - 2003

Explore digital libraries and research issues with insights from Johns Hopkins University's Digital Knowledge Center. Learn about automated tools, systems, and strategies for digitizing print materials.

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

Words Matter: How Language Choices Predict Societal Trends and Outcomes in Media, Health and Policing

Explore how language patterns in media, health discussions, and police interactions predict societal trends and outcomes. Gain insights into communication challenges and their real-world implications.

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

Speech and Dialog Mining on Heterogeneous Data

Explore techniques for analyzing and extracting valuable insights from large volumes of customer interactions, including speech and associated data, to enhance business operations.

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

Visual Semantics Events

Explore ambiguous image classification and multilingual video-text alignment for robust event understanding. Enhance visual models' performance on uncertain data and leverage diverse news sources.

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

Ontological Semantics: An Overview

Explore a comprehensive approach to text meaning in computer processing, covering theories, methodologies, and implementations for effective natural language processing applications.

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

RIR-SF: Room Impulse Response Based Spatial Feature for Multi-channel Multi-talker ASR

Explore a novel spatial feature for multi-channel multi-talker ASR, improving performance in reverberant environments and reducing character error rates by 21.3%.

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

Multimodal Machine Learning for Human-Centric Tasks

Explore novel multimodal architectures for robust solutions in human-centric tasks, addressing missing modalities, noisy features, and leveraging unlabeled data in speech and emotion recognition.

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

Segmentation, Indexing and Retrieval of Multilingual Sources - 2002

Explore techniques for segmenting, indexing, and retrieving multilingual sources, enhancing cross-language information access and processing capabilities.

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

Nugget: Neural Agglomerative Embeddings of Text

Explore dynamic text embedding with Nugget, a novel approach for encoding language into meaningful units, enhancing semantic comparison and expanding contextual windows in language models.

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

Machine Translation - JSALT 2034

Explore machine translation techniques and advancements with expert Ondrej Bojar in this comprehensive JSALT 2034 workshop session.

• YouTube
• 2 hours 52 minutes
• Self-Paced
• Free Video