Zobrazeno 1 - 10
of 11 346
pro vyhledávání: '"van Niekerk 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
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:
Ruppik, Benjamin Matthias, Heck, Michael, van Niekerk, Carel, Vukovic, Renato, Lin, Hsien-chin, Feng, Shutong, Zibrowius, Marcus, Gašić, Milica
A common approach for sequence tagging tasks based on contextual word representations is to train a machine learning classifier directly on these embedding vectors. This approach has two shortcomings. First, such methods consider single input sequenc
Externí odkaz:
http://arxiv.org/abs/2408.03706
Autor:
Feng, Shutong, Lin, Hsien-chin, Geishauser, Christian, Lubis, Nurul, van Niekerk, Carel, Heck, Michael, Ruppik, Benjamin, Vukovic, Renato, Gašić, Milica
Emotions are indispensable in human communication, but are often overlooked in task-oriented dialogue (ToD) modelling, where the task success is the primary focus. While existing works have explored user emotions or similar concepts in some ToD tasks
Externí odkaz:
http://arxiv.org/abs/2408.02417
Autor:
Vukovic, Renato, Arps, David, van Niekerk, Carel, Ruppik, Benjamin Matthias, Lin, Hsien-Chin, Heck, Michael, Gašić, Milica
State-of-the-art task-oriented dialogue systems typically rely on task-specific ontologies for fulfilling user queries. The majority of task-oriented dialogue data, such as customer service recordings, comes without ontology and annotation. Such onto
Externí odkaz:
http://arxiv.org/abs/2408.02361
Autor:
Craft, Clayton L., Barton, Nicholas J., Klug, Andrew C., Scalzi, Kenneth, Wildemann, Ian, Asagodu, Pramod, Broz, Joseph D., Porto, Nikola L., Macalik, Michael, Rizzo, Anthony, Percevault, Garrett, Tison, Christopher C., Smith, A. Matthew, Fanto, Michael L., Schneeloch, James, Sheridan, Erin, Heberle, Dylan, Brownell, Andrew, Sundaram, Vijay S. S., Deenadayalan, Venkatesh, van Niekerk, Matthew, Manfreda-Schulz, Evan, Howland, Gregory A., Preble, Stefan F., Coleman, Daniel, Leake, Gerald, Antohe, Alin, Vo, Tuan, Fahrenkopf, Nicholas M., Stievater, Todd H., Brickman-Soderberg, Kathy-Anne, Smith, Zachary S., Hucul, David
Reliable control of quantum information in matter-based qubits requires precisely applied external fields, and unaccounted for spatial cross-talk of these fields between adjacent qubits leads to loss of fidelity. We report a CMOS foundry-produced, mi
Externí odkaz:
http://arxiv.org/abs/2406.17607
This paper introduces the R package INLAjoint, designed as a toolbox for fitting a diverse range of regression models addressing both longitudinal and survival outcomes. INLAjoint relies on the computational efficiency of the integrated nested Laplac
Externí odkaz:
http://arxiv.org/abs/2402.08335
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
Autor:
Sterrantino, Anna Freni, Rustand, Denis, van Niekerk, Janet, Krainski, Elias Teixeira, Rue, Håvard
In this work, we present a new approach for constructing models for correlation matrices with a user-defined graphical structure. The graphical structure makes correlation matrices interpretable and avoids the quadratic increase of parameters as a fu
Externí odkaz:
http://arxiv.org/abs/2312.06289
The integrated nested Laplace approximations (INLA) method has become a widely utilized tool for researchers and practitioners seeking to perform approximate Bayesian inference across various fields of application. To address the growing demand for i
Externí odkaz:
http://arxiv.org/abs/2311.08050