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

Behavioral, Neuroscience, and Computational Methods in the Study of Human Speech

Explore modality-specific speech processing through behavioral, brain imaging, and computational methods. Discover evidence challenging conventional theories of abstract linguistic encoding in speech perception.

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

From Bases to Exemplars, and From Separation to Understanding

Explore audio source separation techniques, from basis functions to exemplars, and learn how to achieve direct computation of tasks like noisy speech recognition without intermediate separation steps.

• YouTube
• 1 hour 16 minutes
• On-Demand
• Free Video

Hearing Without Listening: Voice Authentication with Privacy

Explore voice authentication privacy challenges and solutions, including cryptographic methods and secure binary embeddings for protecting user voice prints while enabling authentication.

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

Towards a Computational Model of Human Speech Recognition

Explore computational approaches to speech recognition based on distinctive features, incorporating statistical learning models guided by human speech production and perception.

• YouTube
• 1 hour 32 minutes
• On-Demand
• Free Video

My Adventures With Speech - 2013

Explore a 40-year journey in speech research, delving into personal insights, challenges, and breakthroughs in understanding human communication through speech.

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

Context-Sensitivity and Stochastic Unification-Based Grammars - 2000

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
• On-Demand
• Free Video

Do Pretrained Transformers Learn In-Context by Gradient Descent?

Explore the relationship between In-Context Learning and Gradient Descent in large language models, examining theoretical connections and empirical evidence from pre-trained transformers.

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

Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts?

Explore speaker attribution in transcribed speech, examining challenges and proposing a new benchmark for conversational speech transcripts. Analyze model performance and impact of transcription style.

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

Kreyòl-MT - Machine Translation for Latin American, Caribbean, and Colonial African Creole Languages

Explore machine translation for Creole languages with Kreyòl-MT, enhancing communication across Latin America, Caribbean, and Colonial Africa. Learn about innovative NLP techniques.

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

The NLP Task Effectiveness of Long-Range Transformers

Explore the effectiveness of long-range Transformer variants on NLP tasks, comparing their performance and analyzing attention behaviors to uncover strengths and limitations.

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

Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models

Explore visual representations in unimodal and multimodal models, comparing their strengths in label prediction and dense prediction tasks. Gain insights into language's role in visual learning.

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

Defending Against Disinformation Attacks in Open-Domain Question Answering

Explore defensive strategies against adversarial poisoning in open-domain question answering systems, focusing on query augmentation and a novel confidence method for improved accuracy.

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

NevIR: Negation in Neural Information Retrieval

Explore negation's impact on neural information retrieval models, analyzing performance across architectures and proposing strategies to improve handling of negated queries.

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

Large-Scale Bitext Corpora Provide New Evidence for Cognitive Representations of Spatial Terms

Explore cognitive representations of spatial terms using large-scale bitext corpora, examining geometric vs. functional classes and their cross-linguistic variability.

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

Multilingual Representation Distillation with Contrastive Learning

Explore multilingual sentence representations and contrastive learning for cross-lingual tasks, focusing on quality estimation of parallel sentences and similarity search in low-resource languages.

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