Related papers: A Proposal for Proquints: Identifiers that are Rea…
Norm-aware recommender systems have gained increased attention, especially for diversity optimization. The recommender systems community has well-established experimentation pipelines that support reproducible evaluations by facilitating…
Large language models have shown unprecedented abilities in generating linguistically coherent and syntactically correct natural language output. However, they often return incorrect and inconsistent answers to input questions. Due to the…
Despite renewed awareness of the importance of articulation, it remains a challenge for instructors to handle the pronunciation needs of language learners. There are relatively scarce pedagogical tools for pronunciation teaching and…
Speech language models refer to language models with speech processing and understanding capabilities. One key desirable capability for speech language models is the ability to capture the intricate interdependency between content and…
Propositional logics in general, considered as a set of sentences, can be undecidable even if they have "nice" representations, e.g., are given by a calculus. Even decidable propositional logics can be computationally complex (e.g., already…
Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose ConsSent, a simple yet surprisingly powerful unsupervised method to learn such representations by enforcing…
In this paper we explore the use of unsupervised methods for detecting cognates in multilingual word lists. We use online EM to train sound segment similarity weights for computing similarity between two words. We tested our online systems…
Given two combinatorial identities proved earlier, a new set of variations of these combinatorial identities is listed and proved with the integral representation method. Some identities from literature are shown to be special cases of…
We propose a method for learning de-identified prosody representations from raw audio using a contrastive self-supervised signal. Whereas prior work has relied on conditioning models on bottlenecks, we introduce a set of inductive biases…
Fine-grained editing of speech attributes$\unicode{x2014}$such as prosody (i.e., the pitch, loudness, and phoneme durations), pronunciation, speaker identity, and formants$\unicode{x2014}$is useful for fine-tuning and fixing imperfections…
Identifying words which may cause difficulty for a reader is an essential step in most lexical text simplification systems prior to lexical substitution and can also be used for assessing the readability of a text. This task is commonly…
The goal of this work is to establish a scalable pipeline for expanding an object detector towards novel/unseen categories, using zero manual annotations. To achieve that, we make the following four contributions: (i) in pursuit of…
Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but…
We explore a method for presenting word suggestions for non-visual text input using simultaneous voices. We conduct two perceptual studies and investigate the impact of different presentations of voices on a user's ability to detect which…
Prominences and boundaries are the essential constituents of prosodic structure in speech. They provide for means to chunk the speech stream into linguistically relevant units by providing them with relative saliences and demarcating them…
Large language models (LLMs), endowed with exceptional reasoning capabilities, are adept at discerning profound user interests from historical behaviors, thereby presenting a promising avenue for the advancement of recommendation systems.…
A permutiple is the product of a digit preserving multiplication, that is, a number which is an integer multiple of some permutation of its digits. Certain permutiple problems, particularly transposable, cyclic, and, more recently,…
Generative recommender systems have recently attracted attention by formulating next-item prediction as an autoregressive sequence generation task. However, most existing methods optimize standard next-token likelihood and implicitly treat…
We propose a novel model to hierarchically incorporate phoneme and phonotactic information for language identification (LID) without requiring phoneme annotations for training. In this model, named PHO-LID, a self-supervised phoneme…
The labelling of speech corpora is a laborious and time-consuming process. The ProsoBeast Annotation Tool seeks to ease and accelerate this process by providing an interactive 2D representation of the prosodic landscape of the data, in…