Embedded speech recognition systems

Show simple item record

dc.contributor.advisor Dr. Waleed Abdulla en
dc.contributor.advisor Prof. Zoran Salcic en
dc.contributor.author Cheng, Octavian en
dc.date.accessioned 2008-12-16T22:47:30Z en
dc.date.available 2008-12-16T22:47:30Z en
dc.date.issued 2008 en
dc.identifier.citation Thesis (PhD--Electrical and Electronic Engineering)--University of Auckland, 2008. en
dc.identifier.uri http://hdl.handle.net/2292/3279 en
dc.description.abstract Apart from recognition accuracy, decoding speed and vocabulary size, another point of consideration when developing a practical ASR application is the adaptability of the system. An ASR system is more useful if it can cope with changes that are introduced by users, for example, new words and new grammar rules. In addition, the system can also automatically update the underlying knowledge sources, such as language model probabilities, for better recognition accuracy. Since the knowledge sources need to be adaptable, it is in°exible to statically combine them. It is because on-line modi¯cation becomes di±cult once all the knowledge sources have been combined into one static search space. The second objective of the thesis is to develop an algorithm which allows dynamic integration of knowledge sources during decoding. In this approach, each knowledge source is represented by a weighted ¯nite state transducer (WFST). The knowledge source that is subject to adaptation is factorized from the entire search space. The adapted knowledge source is then combined with the others during decoding. In this thesis, we propose a generalized dynamic WFST composition algorithm, which avoids the creation of non- coaccessible paths, performs weight look-ahead and does not impose any constraints to the topology of the WFSTs. Experimental results on Wall Street Journal (WSJ1) 20k- word trigram task show that our proposed approach has a better word accuracy versus real-time factor characteristics than other dynamic composition approaches. en
dc.language.iso en en
dc.publisher ResearchSpace@Auckland en
dc.relation.ispartof PhD Thesis - University of Auckland en
dc.relation.isreferencedby UoA1848323 en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. en
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm en
dc.rights.uri http://creativecommons.org/licenses/by-nc-sa/3.0/nz/ en
dc.subject Speech Recognition en
dc.subject Embedded Systems en
dc.title Embedded speech recognition systems en
dc.type Thesis en
thesis.degree.discipline Electrical and Electronic Engineering en
thesis.degree.grantor The University of Auckland en
thesis.degree.level Doctoral en
thesis.degree.name PhD en
dc.subject.marsden Fields of Research::290000 Engineering and Technology::290900 Electrical and Electronic Engineering en
dc.rights.holder Copyright: The author en
pubs.local.anzsrc 0906 - Electrical and Electronic Engineering en
pubs.org-id Faculty of Engineering en
dc.identifier.wikidata Q112877149

Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record


Search ResearchSpace