2 Search Results for "De Sa, Christopher"


Document
Robust Phoneme Recognition with Little Data

Authors: Christopher Dane Shulby, Martha Dais Ferreira, Rodrigo F. de Mello, and Sandra Maria Aluisio

Published in: OASIcs, Volume 74, 8th Symposium on Languages, Applications and Technologies (SLATE 2019)


Abstract
A common belief in the community is that deep learning requires large datasets to be effective. We show that with careful parameter selection, deep feature extraction can be applied even to small datasets.We also explore exactly how much data is necessary to guarantee learning by convergence analysis and calculating the shattering coefficient for the algorithms used. Another problem is that state-of-the-art results are rarely reproducible because they use proprietary datasets, pretrained networks and/or weight initializations from other larger networks. We present a two-fold novelty for this situation where a carefully designed CNN architecture, together with a knowledge-driven classifier achieves nearly state-of-the-art phoneme recognition results with absolutely no pretraining or external weight initialization. We also beat the best replication study of the state of the art with a 28% FER. More importantly, we are able to achieve transparent, reproducible frame-level accuracy and, additionally, perform a convergence analysis to show the generalization capacity of the model providing statistical evidence that our results are not obtained by chance. Furthermore, we show how algorithms with strong learning guarantees can not only benefit from raw data extraction but contribute with more robust results.

Cite as

Christopher Dane Shulby, Martha Dais Ferreira, Rodrigo F. de Mello, and Sandra Maria Aluisio. Robust Phoneme Recognition with Little Data. In 8th Symposium on Languages, Applications and Technologies (SLATE 2019). Open Access Series in Informatics (OASIcs), Volume 74, pp. 4:1-4:11, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{shulby_et_al:OASIcs.SLATE.2019.4,
  author =	{Shulby, Christopher Dane and Ferreira, Martha Dais and de Mello, Rodrigo F. and Aluisio, Sandra Maria},
  title =	{{Robust Phoneme Recognition with Little Data}},
  booktitle =	{8th Symposium on Languages, Applications and Technologies (SLATE 2019)},
  pages =	{4:1--4:11},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-114-6},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{74},
  editor =	{Rodrigues, Ricardo and Janou\v{s}ek, Jan and Ferreira, Lu{\'\i}s and Coheur, Lu{\'\i}sa and Batista, Fernando and Gon\c{c}alo Oliveira, Hugo},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/OASIcs.SLATE.2019.4},
  URN =		{urn:nbn:de:0030-drops-108715},
  doi =		{10.4230/OASIcs.SLATE.2019.4},
  annote =	{Keywords: feature extraction, acoustic modeling, phoneme recognition, statistical learning theory}
}
Document
A Formal Framework for Probabilistic Unclean Databases

Authors: Christopher De Sa, Ihab F. Ilyas, Benny Kimelfeld, Christopher Ré, and Theodoros Rekatsinas

Published in: LIPIcs, Volume 127, 22nd International Conference on Database Theory (ICDT 2019)


Abstract
Most theoretical frameworks that focus on data errors and inconsistencies follow logic-based reasoning. Yet, practical data cleaning tools need to incorporate statistical reasoning to be effective in real-world data cleaning tasks. Motivated by empirical successes, we propose a formal framework for unclean databases, where two types of statistical knowledge are incorporated: The first represents a belief of how intended (clean) data is generated, and the second represents a belief of how noise is introduced in the actual observed database. To capture this noisy channel model, we introduce the concept of a Probabilistic Unclean Database (PUD), a triple that consists of a probabilistic database that we call the intention, a probabilistic data transformator that we call the realization and captures how noise is introduced, and an observed unclean database that we call the observation. We define three computational problems in the PUD framework: cleaning (infer the most probable intended database, given a PUD), probabilistic query answering (compute the probability of an answer tuple over the unclean observed database), and learning (estimate the most likely intention and realization models of a PUD, given examples as training data). We illustrate the PUD framework on concrete representations of the intention and realization, show that they generalize traditional concepts of repairs such as cardinality and value repairs, draw connections to consistent query answering, and prove tractability results. We further show that parameters can be learned in some practical instantiations, and in fact, prove that under certain conditions we can learn a PUD directly from a single dirty database without any need for clean examples.

Cite as

Christopher De Sa, Ihab F. Ilyas, Benny Kimelfeld, Christopher Ré, and Theodoros Rekatsinas. A Formal Framework for Probabilistic Unclean Databases. In 22nd International Conference on Database Theory (ICDT 2019). Leibniz International Proceedings in Informatics (LIPIcs), Volume 127, pp. 6:1-6:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{desa_et_al:LIPIcs.ICDT.2019.6,
  author =	{De Sa, Christopher and Ilyas, Ihab F. and Kimelfeld, Benny and R\'{e}, Christopher and Rekatsinas, Theodoros},
  title =	{{A Formal Framework for Probabilistic Unclean Databases}},
  booktitle =	{22nd International Conference on Database Theory (ICDT 2019)},
  pages =	{6:1--6:18},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-101-6},
  ISSN =	{1868-8969},
  year =	{2019},
  volume =	{127},
  editor =	{Barcelo, Pablo and Calautti, Marco},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.ICDT.2019.6},
  URN =		{urn:nbn:de:0030-drops-103083},
  doi =		{10.4230/LIPIcs.ICDT.2019.6},
  annote =	{Keywords: Unclean databases, data cleaning, probabilistic databases, noisy channel}
}
  • Refine by Author
  • 1 Aluisio, Sandra Maria
  • 1 De Sa, Christopher
  • 1 Ferreira, Martha Dais
  • 1 Ilyas, Ihab F.
  • 1 Kimelfeld, Benny
  • Show More...

  • Refine by Classification
  • 1 Computing methodologies → Speech recognition
  • 1 Theory of computation → Data modeling
  • 1 Theory of computation → Incomplete, inconsistent, and uncertain databases

  • Refine by Keyword
  • 1 Unclean databases
  • 1 acoustic modeling
  • 1 data cleaning
  • 1 feature extraction
  • 1 noisy channel
  • Show More...

  • Refine by Type
  • 2 document

  • Refine by Publication Year
  • 2 2019

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail