Social annotation tools hold great potential in facilitating students' academic reading by
transforming solitary reading tasks into collaborative experience, but little is known about …

Negation is poorly captured by current language models, although the extent of this problem
is not widely understood. We introduce a natural language inference (NLI) test suite to …

There is an old quip in mathematics about how to get to infinity—just keep adding one. Silly
as it is, that quip articulates two of the central themes of the present paper:(1) big …

The present study aims at predicting the speech fluency of children using automatic acoustic
measures derived from forward-backward divergence segmentation (FBDS). Thirteen …

The shift from one-hot to distributed representation, popularly referred to as word embedding
has changed the landscape of natural language processing (nlp) and information retrieval …

Silent speech interfaces (SSIs) enable speech recognition and synthesis in the absence of
an acoustic signal. Yet, the archetypal SSI fails to convey the expressive attributes of …

Large language models (LLMs) are found to have the ability of in-context generation (ICG):
when they are fed with an in-context prompt concatenating a few somehow similar …

This study aimed to adapt and validate the Word Complexity Measure (WCM) for Persian-
speaking toddlers. The WCM is a tool for assessing phonological complexity, originally …

Objectives This study investigates the role of sentence stress on the comprehension of
sentences with clitic pronouns (unstressed morphemes and a typical feature of Romance …

Voice conversion aims to transform source speech into a different target voice. However,
typical voice conversion systems do not account for rhythm, which is an important factor in …