Dissertation/Thesis Abstract

Multi-Task and Transfer Learning in Low-Resource Speech Recognition
by Meyer, Josh, Ph.D., The University of Arizona, 2019, 172; 22615820
Abstract (Summary)

This thesis investigates methods for Acoustic Modeling in Automatic Speech Recognition, assuming limited access to training data in the target domain. The Acoustic Models of interest are Deep Neural Network Acoustic Models (in both the Hybrid and End-to-End approaches), and the target domains in question are either different languages or different speakers. Inductive bias is transfered from a source domain during training, via Multi-Task Learning or Transfer Learning.

With regards to Multi-Task Learning, Chapter (5) presents experiments which explicitly incorporate linguistic knowledge (i.e. phonetics and phonology) into an auxiliary task during neural Acoustic Model training. In Chapter (6), I investigate Multi-Task methods which do not rely on expert knowledge (linguistic or otherwise), by re-using existing parts of the Hybrid training pipeline. In Chapter (7), new tasks are discovered using unsupervised learning. In Chapter (8), using the “copy-paste” Transfer Learning approach, I demonstrate that with an appropriate early-stopping criteria, cross-lingual transfer is possible to both large and small target datasets.

The methods and intuitions which rely on linguistic knowledge are of interest to the Speech Recognition practitioner working in low-resource domains. These same sections may be of interest to the theoretical linguist, as a study of the relative import of phonetic categories in classification. To the Machine Learning practitioner, I hope to offer approaches which can be easily ported over to other classification tasks. To the Machine Learning researcher, I hope to inspire new ideas on addressing the small data problem.

Indexing (document details)
Advisor: Bever, Thomas, Surdeanu, Mihai
Commitee: Hammond, Michael, Morrison, Clayton
School: The University of Arizona
Department: Linguistics
School Location: United States -- Arizona
Source: DAI-A 81/2(E), Dissertation Abstracts International
Source Type: DISSERTATION
Subjects: Artificial intelligence, Linguistics
Keywords: Automatic speech recognition, Deep neural networks, Low-resource languages, Multi-task learning, Transfer learning
Publication Number: 22615820
ISBN: 9781085750882
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest