%Aigaion2 BibTeX export from Idiap Publications %Saturday 21 December 2024 04:35:17 PM @TECHREPORT{Luyet_Idiap-RR-04-2016, author = {Luyet, Gil and Dighe, Pranay and Asaei, Afsaneh and Bourlard, Herv{\'{e}}}, keywords = {automatic speech recognition (ASR), Deep neural network (DNN) , k-nearest neighbor (kNN) search , low-rank representation (LRR) , posterior probability }, projects = {Idiap}, month = {3}, title = {Low-Rank Representation of Nearest Neighbor Phone Posterior Probabilities to Enhance DNN Acoustic Modeling}, type = {Idiap-RR}, number = {Idiap-RR-04-2016}, year = {2016}, institution = {Idiap}, abstract = {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.}, pdf = {https://publications.idiap.ch/attachments/reports/2016/Luyet_Idiap-RR-04-2016.pdf} }