Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 1, 2014

Singular value decomposition based low-footprint speaker adaptation and personalization for deep neural network

View Full Paper
Ask AI
Bookmark
Share

Authors

JXJian XueXi'an University of Science and TechnologyJLJinyu LiMicrosoft (United States)DYDong YuSeattle University

Discussion

Loading...

Member takes

Implication

Key Points

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

Cite This Study

Xue et al. (2014) studied this question.

synapsesocial.com/papers/6a0f507a34fbf15957ed1dd9https://doi.org/10.1109/icassp.2014.6854828
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. 1Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems2010 · 159 citations
  2. 2Large vocabulary continuous speech recognition with context-dependent DBN-HMMS2011 · 181 citations
  3. 3Adaptation of context-dependent deep neural networks for automatic speech recognition2012 · 204 citations
  4. 4KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition2013 · 421 citations
  5. 5Auto-encoder bottleneck features using deep belief networks2012 · 185 citations