Multitask Learning of Deep Neural Networks for Low-Resource Speech Recognition - 2015


We propose a multitask learning (MTL) approach to enhance low-resource automatic speech recognition using deep neural networks (DNNs) while not requiring further language resources. We 1st demonstrate that the performance of the phone models of one low-resource language can be improved by coaching its grapheme models in parallel beneath the MTL framework. If multiple low-resource languages are trained along, we investigate learning a collection of universal phones (UPS) as a further task again within the MTL framework to boost the performance of the phone models of all the involved languages. In both cases, the heuristic guideline is to select a task that will exploit further data from the coaching information of the primary task(s). In the primary technique, the additional information is that the phone-to-grapheme mappings, whereas in the second method, the UPS helps to implicitly map the phones of the multiple languages among each different. In an exceedingly series of experiments using 3 low-resource South African languages within the Lwazi corpus, the proposed MTL strategies obtain important word recognition gains compared with single-task learning (STL) of the corresponding DNNs or ROVER that mixes results from many STL-trained DNNs.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Egocentric Daily Activity Recognition via Multitask Clustering - 2015 ABSTRACT: Recognizing human activities from videos could be a basic research downside in computer vision. Recently, there was a growing interest
PROJECT TITLE :Guest Editorial Special Issue on the 2015 IEEE International Instrumentation and Measurement Technology Conference Pisa, Italy, May 11–14, 2015ABSTRACT:The thirty second annual IEEE International Instrumentation
PROJECT TITLE :Gabor Cube Selection Based Multitask Joint Sparse Representation for Hyperspectral Image ClassificationABSTRACT:The large quantity of spectral and spatial data contained in hyperspectral imagery has provided nice
PROJECT TITLE :Polarimetric Inverse Scattering via Incremental Sparse Bayesian Multitask LearningABSTRACT:During this letter, we use the sparse Bayesian multitask learning to understand joint sparsity-imposing polarimetric inverse
PROJECT TITLE :A Multitask Learning View on the Earth System Model EnsembleABSTRACT:Earth system models (ESMs) are based on physical principles that are meant to emulate climate behavior. They're the primary mechanisms for getting

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry