Camilo Morales | Searcharxiv

arXiv2022

Minimal ring extensions of the integers exhibiting Kochen-Specker contextuality

This paper is a contribution to the algebraic study of contextuality in quantum theory. As an algebraic analogue of Kochen and Specker's no-hidden-variables result, we investigate rational subrings over which the partial ring of $d \times d$ symmetric matrices ($d \geq 3$) admits no morphism to a commutative ring, which we view as an "algebraic hidden state." For $d = 3$, the minimal such ring is shown to be $\mathbb{Z}[1/6]$, while for $d \geq 6$ the minimal subring is $\mathbb{Z}$ itself. The proofs rely on the construction of new sets of integer vectors in dimensions 3 and 6 that have no Kochen-Specker coloring.

math.NT↗

arXiv2017

Use of Knowledge Graph in Rescoring the N-Best List in Automatic Speech Recognition

With the evolution of neural network based methods, automatic speech recognition (ASR) field has been advanced to a level where building an application with speech interface is a reality. In spite of these advances, building a real-time speech recogniser faces several problems such as low recognition accuracy, domain constraint, and out-of-vocabulary words. The low recognition accuracy problem is addressed by improving the acoustic model, language model, decoder and by rescoring the N-best list at the output of the decoder. We are considering the N-best list rescoring approach to improve the recognition accuracy. Most of the methods in the literature use the grammatical, lexical, syntactic and semantic connection between the words in a recognised sentence as a feature to rescore. In this paper, we have tried to see the semantic relatedness between the words in a sentence to rescore the N-best list. Semantic relatedness is computed using TransE~\cite{bordes2013translating}, a method for low dimensional embedding of a triple in a knowledge graph. The novelty of the paper is the application of semantic web to automatic speech recognition.

cs.CL↗