Logo: to the web site of Uppsala University

uu.sePublications from Uppsala University
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Time-Varying Normalizing Flows for Dynamical Signals
KTH Royal Institute of Technology.ORCID iD: 0000-0001-6612-6923
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Automatic control. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Systems and Control. (Systems and Control)ORCID iD: 0000-0001-5474-7060
KTH Royal Institute of Technology.ORCID iD: 0000-0003-2638-6047
2022 (English)Conference paper, Published paper (Refereed)
Abstract [en]

We develop a time-varying normalizing flow (TVNF) for explicit generative modeling of dynamical signals. Being explicit, it can generate samples of dynamical signals, and compute the likelihood of a (given) dynamical signal sample. In the proposed model, signal flow in the layers of the normalizing flow is a function of time, which is realized using an encoded representation that is the output of a recurrent neural network (RNN). Given a set of dynamical signals, the parameters of TVNF are learned according to a maximum-likelihood approach in conjunction with gradient descent (backpropagation). Use of the proposed model is illustrated for a toy application scenario-maximum-likelihood based speech-phone classification task.

Place, publisher, year, edition, pages
2022.
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:uu:diva-481032OAI: oai:DiVA.org:uu-481032DiVA, id: diva2:1685028
Conference
2022 30th European Signal Processing Conference (EUSIPCO 2022)
Available from: 2022-07-31 Created: 2022-07-31 Last updated: 2022-11-04Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

https://ieeexplore.ieee.org/document/9909640

Authority records

Abdalmoaty, Mohamed

Search in DiVA

By author/editor
Anubhab, GhoshAbdalmoaty, MohamedChatterjee, Saikat
By organisation
Automatic controlDivision of Systems and Control
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 99 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf