Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Reports, Documentation, and Standards
  4. Low-Rank Representation of Nearest Neighbor Phone Posterior Probabilities to Enhance DNN Acoustic Modeling
 
report

Low-Rank Representation of Nearest Neighbor Phone Posterior Probabilities to Enhance DNN Acoustic Modeling

Luyet, Gil
•
Dighe, Pranay
•
Asaei, Afsaneh  
Show more
2016

We hypothesize that optimal deep neural networks (DNN) class-conditional posterior probabilities live in a union of low-dimensional subspaces. In real test conditions, DNN posteriors encode uncertainties which can be regarded as a superposition of unstructured sparse noise to the optimal posteriors. We aim to investigate different ways to structure the DNN outputs exploiting low-rank representation (LRR) techniques. Using a large number of training posterior vectors, the underlying low-dimensional subspace is identified through nearest neighbor analysis, and low-rank decomposition enables separation of the ``optimal'' posteriors from the spurious uncertainties at the DNN output. Experiments demonstrate that by processing subsets of posteriors which possess strong subspace similarity, low-rank representation enables enhancement of posterior probabilities, and lead to higher speech recognition accuracy based on the hybrid DNN-hidden Markov model (HMM) system.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

LRR.pdf

Access type

openaccess

Size

218.66 KB

Format

Adobe PDF

Checksum (MD5)

b5fc77e79a8ad306295da93e218c0202

Loading...
Thumbnail Image
Name

Luyet_Idiap-RR-04-2016.pdf

Access type

openaccess

Size

617.03 KB

Format

Adobe PDF

Checksum (MD5)

4d8b493594c656077505d25a1352d19d

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés