Zobrazeno 1 - 10
of 6 168
pro vyhledávání: '"Kamper, A"'
We look at the long-standing problem of segmenting unlabeled speech into word-like segments and clustering these into a lexicon. Several previous methods use a scoring model coupled with dynamic programming to find an optimal segmentation. Here we pr
Externí odkaz:
http://arxiv.org/abs/2409.14486
Given an image query, visually prompted keyword localisation (VPKL) aims to find occurrences of the depicted word in a speech collection. This can be useful when transcriptions are not available for a low-resource language (e.g. if it is unwritten).
Externí odkaz:
http://arxiv.org/abs/2409.06013
In the Naive Bayes classification model the class conditional densities are estimated as the products of their marginal densities along the cardinal basis directions. We study the problem of obtaining an alternative basis for this factorisation with
Externí odkaz:
http://arxiv.org/abs/2409.05635
Autor:
Jørgensen, Frederik Kamper, Kjellgren, Erik Rosendahl, Jensen, Hans Jørgen Aagaard, Hedegård, Erik Donovan
We present the theory and implementation of a novel, fully variational wave function - density functional theory (DFT) hybrid model, which is applicable to many cases of strong correlation. We denote this model the multiconfigurational self-consisten
Externí odkaz:
http://arxiv.org/abs/2409.05213
Discovering a lexicon from unlabeled audio is a longstanding challenge for zero-resource speech processing. One approach is to search for frequently occurring patterns in speech. We revisit this idea with DUSTED: Discrete Unit Spoken-TErm Discovery.
Externí odkaz:
http://arxiv.org/abs/2408.14390
Autor:
Oneata, Dan, Kamper, Herman
Visually grounded speech models link speech to images. We extend this connection by linking images to text via an existing image captioning system, and as a result gain the ability to map speech audio directly to text. This approach can be used for s
Externí odkaz:
http://arxiv.org/abs/2406.07133
We propose a novel mechanism for generating single photons in the mid-Infrared (MIR) using a solid-state or molecular quantum emitter. The scheme utilises cavity QED effects to selectively enhance a Frank-Condon transition, deterministically preparin
Externí odkaz:
http://arxiv.org/abs/2405.12777
Autor:
Lu, I-Te, Shin, Dongbin, Svendsen, Mark Kamper, Hübener, Hannes, De Giovannini, Umberto, Latini, Simone, Ruggenthaler, Michael, Rubio, Angel
Strong laser pulses can control superconductivity, inducing non-equilibrium transient pairing by leveraging strong-light matter interaction. Here we demonstrate theoretically that equilibrium ground-state phonon-mediated superconductive pairing can b
Externí odkaz:
http://arxiv.org/abs/2404.08122
When children learn new words, they employ constraints such as the mutual exclusivity (ME) bias: a novel word is mapped to a novel object rather than a familiar one. This bias has been studied computationally, but only in models that use discrete wor
Externí odkaz:
http://arxiv.org/abs/2403.13922
Autor:
Kamper, Herman, van Niekerk, Benjamin
We revisit a self-supervised method that segments unlabelled speech into word-like segments. We start from the two-stage duration-penalised dynamic programming method that performs zero-resource segmentation without learning an explicit lexicon. In t
Externí odkaz:
http://arxiv.org/abs/2401.17902