A translation framework for discovering word-like units from visual scenes and spoken descriptions

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.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2020

Author dc:creator

• Wang, Liming

Contributors dc:contributor

• Hasegawa-Johnson, Mark A

• machine translation
• multimodal learning
• low-resource speech technology

Statement dc:rights

• Copyright 2020 Liming Wang

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/108055

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/108055