Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 2 of 2 for “"Universal feature learning"”.
-
Learning Feature Representation for Automatic Speech Recognition
Feature extraction in automatic speech recognition (ASR) can be regarded as learning representations from lower-level to more abstract higher-level features. Lower-level feature can be viewed as features from the signal domain, such as perceptual linear predictive (PLP) and Mel-frequency cepstral …
-
Exploring the generalization capabilities of deep learning architectures for universal image feature learning
… challenges regarding the generalization and universality of the information extracted from them. These challenges mainly revolve around knowledge transfer, a popular and powerful method where a network trained on one dataset is applied to another dataset or application with similar or …