कोर्स
6076 कोर्स
Speech Recognition
Explore speech recognition fundamentals and techniques with expert insights from Johns Hopkins University's language processing center.
2003 CLSP Summer Workshop Review - Confidence Estimation
Explore confidence estimation techniques in speech and language processing through this comprehensive workshop review from Johns Hopkins University's renowned CLSP program.
Robust Representation of Attended Speech in Human Brain with Implications for ASR
Discover how the human brain processes attended speech and its applications for advancing automatic speech recognition technology.
Improving Machine Translation by Propagating Uncertainty
Discover how uncertainty propagation enhances machine translation accuracy through advanced computational techniques and statistical modeling approaches.
Factored Adaptation for Separating Speaker and Environment Variability
Explore factored adaptation techniques for separating speaker and environment variability in speech processing with Microsoft Research expert Mike Seltzer.
Grounding Language in the World - A Framework for Signs and Actions
Explore how language connects to real-world experiences through a comprehensive framework linking signs, actions, and meaning in cognitive systems.
Measuring and Using Speech Production Information
Explore advanced techniques for measuring and analyzing speech production data to understand human vocal mechanisms and improve speech technology applications.
Fast, Accurate and Robust Multilingual Syntactic Analysis
Discover fast, accurate multilingual syntactic analysis techniques for robust natural language processing across diverse languages and computational environments.
Inducing Synchronous Grammars for Machine Translation
Discover how to induce synchronous grammars for machine translation through advanced computational linguistics techniques and statistical modeling approaches.
Machine Translation - Lecture 1
Discover the fundamentals of machine translation systems and computational linguistics techniques in this comprehensive academic lecture from Johns Hopkins University.
On Representing Acoustics of Speech for Speech Processing
Discover how to represent speech acoustics for processing applications through insights from renowned researcher Bishnu Atal in this comprehensive seminar.
Embracing Language Diversity - Unsupervised Multilingual Learning
Discover unsupervised multilingual learning techniques and language diversity approaches in natural language processing from MIT's Regina Barzilay.