Search Results for author:
Found 7 papers, 2 papers with code
Leveraging Speech for Gesture Detection in Multimodal Communication
Our findings indicate that expanding the speech buffer beyond visual time segments improves performance and that multimodal integration using cross-modal and early fusion techniques outperforms baseline methods using unimodal and late fusion methods.
Co-Speech Gesture Detection through Multi-Phase Sequence Labeling
Yet, the prevalent approach to automatic gesture detection treats the problem as binary classification, classifying a segment as either containing a gesture or not, thus failing to capture its inherently sequential and contextual nature.
Making sense of spoken plurals
Our goal is to compare two models for the conceptualization of plurality.
Semantic properties of English nominal pluralization: Insights from word embeddings
In comparison with our approach, a method from compositional distributional semantics, called FRACSS, predicted plural vectors that were more similar to the corpus-extracted plural vectors in terms of direction but not vector length.
Efficient Dependency Graph Matching with the IMS Open Corpus Workbench
State-of-the-art dependency representations such as the Stanford Typed Dependencies may represent the grammatical relations in a sentence as directed, possibly cyclic graphs.
