Files in this item



application/pdfWANG-THESIS-2020.pdf (2MB)
(no description provided)PDF


Title:A translation framework for discovering word-like units from visual scenes and spoken descriptions
Author(s):Wang, Liming
Advisor(s):Hasegawa-Johnson, Mark A
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):multimodal learning
low-resource speech technology
machine translation
Abstract:In the absence of dictionaries, translators, or grammars, it is still possible to learn some of the words of a new language by listening to spoken descriptions of images. If several images, each containing a particular visually salient object, each co-occur with a particular sequence of speech sounds, we can infer that those speech sounds are a word whose definition is the visible object. A multimodal word discovery system accepts, as input, a database of spoken descriptions of images (or a set of corresponding phone transcriptions) and learns a mapping from waveform segments (or phone strings) to their associated image concepts. In this thesis, we propose a novel framework for multimodal word discovery systems based on statistical machine translation (SMT) and neural machine translation (NMT). We extend the existing theoretical frameworks on unsupervised word discovery and demonstrate a class of effective models for end-to-end word discovery from image regions and spoken descriptions. Finally, we provide a careful ablation study on components of my system and present some of the challenges in multimodal spoken word discovery.
Issue Date:2020-05-14
Rights Information:Copyright 2020 Liming Wang
Date Available in IDEALS:2020-08-26
Date Deposited:2020-05

This item appears in the following Collection(s)

Item Statistics