Center for Language and Speech Processing

Events

Larry Heck (Georgia Institute of Technology) “The AVA Digital Human: Improving Conversational Interactions through Visually Situated Context”

April 4, 2023
When: April 14, 2023 @ 12:00 pm – 1:15 pm
Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Advances in open domain Large Language Models (LLMs) starting with BERT and more recently with GPT-4, PaLM, and LLaMA have facilitated dramatic improvements in conversational systems. These improvements include an unprecedented breadth of conversational[…]

Read More

Student Seminar – Samik Sadhu (JHU) “Importance of Different Temporal Modulations of Speech: A Tale of Two Perspectives”

March 13, 2023
When: April 3, 2023 @ 12:00 pm – 1:15 pm
Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract How important are different temporal speech modulations for speech recognition? We answer this question from two complementary perspectives. Firstly, we quantify the amount of phonetic information in the modulation spectrum of speech by computing[…]

Read More

Emily Prud’hommeaux (Boston College) “Endangered or Just Under-Resourced? Evaluating ASR Quality and Utility When Data is Scarce”

March 13, 2023
When: March 31, 2023 @ 12:00 pm – 1:15 pm
Where: Hackerman Hall B17, 3400 N. Charles Street, Baltimore, MD 21218

Abstract Despite many recent advances in automatic speech recognition (ASR), linguists and language communities engaged in language documentation projects continue to face the obstacle of the “transcription bottleneck”. Researchers in NLP typically do not distinguish between[…]

Read More

Subscribe

Subscribe to the CLSP Seminars Mailing List

Upcoming Seminars

Sep
26
Fri
12:00 pm Auditing Memorization, Dissectin... @ Hackerman Hall B17
Auditing Memorization, Dissectin... @ Hackerman Hall B17
Sep 26 @ 12:00 pm – 1:15 pm
Abstract: The widespread adoption of large language models (LLMs) places a responsibility on the AI research community to rigorously study and understand them. In this talk, I will describe my group’s research on analyzing LLMs’[...]
Sep
29
Mon
12:00 pm NUTMEG: Separating Signal From N... @ Hackerman Hall B17
NUTMEG: Separating Signal From N... @ Hackerman Hall B17
Sep 29 @ 12:00 pm – 1:15 pm
Abstract: NLP models often rely on human-labeled data for training and evaluation. Many approaches crowdsource this data from a large number of annotators with varying skills, backgrounds, and motivations, resulting in conflicting annotations. These conflicts[...]
Oct
3
Fri
12:00 pm Propaganda is already influencin... @ Hackerman Hall B17
Propaganda is already influencin... @ Hackerman Hall B17
Oct 3 @ 12:00 pm – 1:15 pm
Abstract Millions of people around the world query (prompt) large language models for information. While several studies have compellingly documented the persuasive potential of these models, there is limited evidence of who or what influences[...]

Center for Language and Speech Processing