Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 1, 2013Open Access

Extracting deep bottleneck features using stacked auto-encoders

View Full Paper
Ask AI
Bookmark
Share

Authors

JGJonas GehringKarlsruhe Institute of TechnologyYMYajie MiaoNortheastern UniversityFMFlorian MetzeKarlsruhe Institute of Technology

Discussion

Loading...

Member takes

Implication

Key Points

Key points are not available for this paper at this time.

Cite This Study

Gehring et al. (2013) studied this question.

synapsesocial.com/papers/6a0fb9754fb650da4ffe713fhttps://doi.org/10.1109/icassp.2013.6638284
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1SWITCHBOARD: telephone speech corpus for research and development1992 · 2,147 citations
  2. 2The Karlsruhe-Verbmobil speech recognition engine2002 · 102 citations
  3. 3A one-pass decoder based on polymorphic linguistic context assignment2005 · 179 citations
  4. 4Auto-encoder bottleneck features using deep belief networks2012 · 185 citations
  5. 5Extracting and composing robust features with denoising autoencoders2008 · 7,456 citations