A study of rank-constrained multilingual DNNS for low-resource ASR

Abstract

Multilingual Deep Neural Networks (DNNs) have been successfully used to exploit out-of-language data to improve under-resourced ASR. In this paper, we improve on a multilingual DNN by utilizing low-rank factorization (LRF) of weight matrices via Singular Value Decomposition (SVD) to sparsify a multilingual DNN. LRF was previously used for monolingual DNNs… (More)
DOI: 10.1109/ICASSP.2016.7472713

Topics

5 Figures and Tables

Statistics

020406020162017
Citations per Year

Citation Velocity: 13

Averaging 13 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Slides referencing similar topics