Related papers: A tentative model for dimensionless phoneme distan…
Tokenization algorithms that merge the units of a base vocabulary into larger, variable-rate units have become standard in natural language processing tasks. This idea, however, has been mostly overlooked when the vocabulary consists of…
We develop further a new geometrical model of a discretized string, proposed in [1] and establish its basic physical properties. The model can be considered as the natural extention of the usual Feynman amplitude of the random walks to…
Self-supervised language and audio models effectively predict brain responses to speech. However, traditional prediction models rely on linear mappings from unimodal features, despite the complex integration of auditory signals with…
In this article, we present a fresh perspective on language, combining ideas from various sources, but mixed in a new synthesis. As in the minimalist program, the question is whether we can formulate an elegant formalism, a universal…
Given a binary nonlinear code, we provide a deterministic algorithm to compute its weight and distance distribution, and in particular its minimum weight and its minimum distance, which takes advantage of fast Fourier techniques. This…
Score matching is a recently developed parameter learning method that is particularly effective to complicated high dimensional density models with intractable partition functions. In this paper, we study two issues that have not been…
This work briefly explores the possibility of approximating spatial distance (alternatively, similarity) between data points using the Isolation Forest method envisioned for outlier detection. The logic is similar to that of isolation: the…
Although many previous studies have carried out multimodal learning with real-time MRI data that captures the audio-visual kinematics of the vocal tract during speech, these studies have been limited by their reliance on multi-speaker…
We propose an estimation approach to analyse correlated functional data which are observed on unequal grids or even sparsely. The model we use is a functional linear mixed model, a functional analogue of the linear mixed model. Estimation…
Linguistic laws constitute one of the quantitative cornerstones of modern cognitive sciences and have been routinely investigated in written corpora, or in the equivalent transcription of oral corpora. This means that inferences of…
Automatic phonemic transcription tools are useful for low-resource language documentation. However, due to the lack of training sets, only a tiny fraction of languages have phonemic transcription tools. Fortunately, multilingual acoustic…
A judicious combination of dictionary learning methods, block sparsity and source recovery algorithm are used in a hierarchical manner to identify the noises and the speakers from a noisy conversation between two people. Conversations are…
Quantifying the distance between datasets is a fundamental question in mathematics and machine learning. We propose \textit{magnitude distance}, a novel distance metric defined on finite datasets using the notion of the \emph{magnitude} of…
Audio signal processing algorithms are frequently assessed through subjective listening tests in which participants directly score degraded signals on a unidimensional numerical scale. However, this approach is susceptible to…
Investigating linguistic relationships on a global scale requires analyzing diverse features such as syntax, phonology and prosody, which evolve at varying rates influenced by internal diversification, language contact, and sociolinguistic…
We study statistical inference on the similarity/distance between two time-series under uncertain environment by considering a statistical hypothesis test on the distance obtained from Dynamic Time Warping (DTW) algorithm. The sampling…
Comparison of $1$-dimensional distance functions is a basic tool in Alexandrov geometry and it is used to characterize spaces with curvature bounded above or below. For the zero curvature bound there is a differential inequality which…
Phonetic error detection, a core subtask of automatic pronunciation assessment, identifies pronunciation deviations at the phoneme level. Speech variability from accents and dysfluencies challenges accurate phoneme recognition, with current…
While significant advancements have been made in music generation and differentiable sound synthesis within machine learning and computer audition, the simulation of instrument vibration guided by physical laws has been underexplored. To…
Speech-to-text alignment is a critical component of neural text to speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line, while non-autoregressive end to end TTS models rely on…