{"id":{"repo_id":"cape-town","oai_identifier":"oai:open.uct.ac.za:11427/5180"},"canonical_url":"https://search.dev.ndltd.org/etd/cape-town/oai:open.uct.ac.za:11427/5180","repository":{"repo_id":"cape-town","name":"University of Cape Town","base_url":"https://open.uct.ac.za/oai/request"},"display":{"title":"An artificial Intelligence Approach to improving Speech Recognition","abstract":"Speech Recognition is a technology with promising applications. However, the performance of current speech recognizers greatly limit their widespread use. Approaches to reducing the word error rate have mainly been associated with statistical techniques. As a consequence, speech recognition results can still contain sentences that are nonsensical. The method proposed here, is to analize the output of any chosen speech recognition system, in order to determine whether a sentence contains syntactic or semantic errors. This is done via a software agent that uses the information from its knowledge base to attempt to correct the errors found. A system was implemented with a small vocabulary speaker-independent continuous speech recognition system, with limited sentence structures. The achieved increase in speech recognition accuracy, shows that there are bene ts in using this approach.","abstract_html":"Speech Recognition is a technology with promising applications. However, the performance of current speech recognizers greatly limit their widespread use. Approaches to reducing the word error rate have mainly been associated with statistical techniques. As a consequence, speech recognition results can still contain sentences that are nonsensical. The method proposed here, is to analize the output of any chosen speech recognition system, in order to determine whether a sentence contains syntactic or semantic errors. This is done via a software agent that uses the information from its knowledge base to attempt to correct the errors found. A system was implemented with a small vocabulary speaker-independent continuous speech recognition system, with limited sentence structures. The achieved increase in speech recognition accuracy, shows that there are bene ts in using this approach.","abstract_has_math":false,"creators":["Lopes, Luis Ramos dos Santos"],"institution":"Department of Electrical Engineering","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Mashao, Daniel","Ventura, Neco"],"committee_chairs":[],"committee_members":[],"year":2009,"date_issued":"2009","date_published":"2009","updated_at":"2026-07-22T22:22:57Z","subjects":[],"languages":["eng"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11427/5180","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Mashao, Daniel","Ventura, Neco"]},{"key":"dc:creator","label":"Author","values":["Lopes, Luis Ramos dos Santos"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-07-31T10:55:06Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-07-31T10:55:06Z"]},{"key":"dc:date.issued","label":"Date","values":["2009"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Department of Electrical Engineering"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Cape Town"]},{"key":"dc:type","label":"Dc Type","values":["Master Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Masters"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["MSc"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11427/5180"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Speech Recognition is a technology with promising applications. However, the performance of current speech recognizers greatly limit their widespread use. Approaches to reducing the word error rate have mainly been associated with statistical techniques. As a consequence, speech recognition results can still contain sentences that are nonsensical. The method proposed here, is to analize the output of any chosen speech recognition system, in order to determine whether a sentence contains syntactic or semantic errors. This is done via a software agent that uses the information from its knowledge base to attempt to correct the errors found. A system was implemented with a small vocabulary speaker-independent continuous speech recognition system, with limited sentence structures. The achieved increase in speech recognition accuracy, shows that there are bene ts in using this approach."]},{"key":"dc:title","label":"Title","values":["An artificial Intelligence Approach to improving Speech Recognition"]}]}],"canonical_facts":{"dc:contributor.advisor":["Mashao, Daniel","Ventura, Neco"],"dc:creator":["Lopes, Luis Ramos dos Santos"],"dc:date.accessioned":["2014-07-31T10:55:06Z"],"dc:date.available":["2014-07-31T10:55:06Z"],"dc:date.issued":["2009"],"dc:description.abstract":["Speech Recognition is a technology with promising applications. However, the performance of current speech recognizers greatly limit their widespread use. Approaches to reducing the word error rate have mainly been associated with statistical techniques. As a consequence, speech recognition results can still contain sentences that are nonsensical. The method proposed here, is to analize the output of any chosen speech recognition system, in order to determine whether a sentence contains syntactic or semantic errors. This is done via a software agent that uses the information from its knowledge base to attempt to correct the errors found. A system was implemented with a small vocabulary speaker-independent continuous speech recognition system, with limited sentence structures. The achieved increase in speech recognition accuracy, shows that there are bene ts in using this approach."],"dc:identifier.uri":["http://hdl.handle.net/11427/5180"],"dc:language.iso":["eng"],"dc:publisher.department":["Department of Electrical Engineering"],"dc:publisher.institution":["University of Cape Town"],"dc:title":["An artificial Intelligence Approach to improving Speech Recognition"],"dc:type":["Master Thesis"],"dc:type.qualificationlevel":["Masters"],"dc:type.qualificationname":["MSc"]},"updated_at":"2026-07-22T22:22:57Z"}