kth.sePublications
System disruptions
We are currently experiencing disruptions on the search portals due to high traffic. We are working to resolve the issue, you may temporarily encounter an error message.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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
Robust classification using hidden markov models and mixtures of normalizing flows
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0001-6612-6923
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0003-0394-1087
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.ORCID iD: 0000-0002-1643-1054
Show others and affiliations
2020 (English)In: 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP), Institute of Electrical and Electronics Engineers (IEEE) , 2020, article id 9231775Conference paper, Published paper (Refereed)
Abstract [en]

We test the robustness of a maximum-likelihood (ML) based classifier where sequential data as observation is corrupted by noise. The hypothesis is that a generative model, that combines the state transitions of a hidden Markov model (HMM) and the neural network based probability distributions for the hidden states of the HMM, can provide a robust classification performance. The combined model is called normalizing-flow mixture model based HMM (NMM-HMM). It can be trained using a combination of expectation-maximization (EM) and backpropagation. We verify the improved robustness of NMM-HMM classifiers in an application to speech recognition.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2020. article id 9231775
Series
IEEE International Workshop on Machine Learning for Signal Processing, ISSN 2161-0363
Keywords [en]
Generative models, Hidden Markov models, Neural networks, Speech recognition, Backpropagation, Learning systems, Maximum likelihood, Maximum principle, Mixtures, Signal processing, Trellis codes, Combined model, Expectation Maximization, Generative model, Hidden state, Mixture model, Robust classification, Sequential data, State transitions
National Category
Probability Theory and Statistics Signal Processing
Identifiers
URN: urn:nbn:se:kth:diva-291596DOI: 10.1109/MLSP49062.2020.9231775ISI: 000630907800045Scopus ID: 2-s2.0-85096485816OAI: oai:DiVA.org:kth-291596DiVA, id: diva2:1539538
Conference
30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020, 21 September 2020 through 24 September 2020, virtual, Espoo21 September 2020 through 24 September 2020
Note

QC 20210324

Part of conference proceedings: ISBN 9781728166629

Available from: 2021-03-24 Created: 2021-03-24 Last updated: 2024-05-02Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Ghosh, AnubhabHonore, AntoineLiu, DongHenter, Gustav EjeChatterjee, Saikat

Search in DiVA

By author/editor
Ghosh, AnubhabHonore, AntoineLiu, DongHenter, Gustav EjeChatterjee, Saikat
By organisation
Information Science and EngineeringSpeech, Music and Hearing, TMHACCESS Linnaeus Centre
Probability Theory and StatisticsSignal Processing

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 248 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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