Improving black-box speech-to-text systems via machine learning techniques
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Tipo de documento: | Trabalho de conclusão de curso |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/147632 |
Resumo: | There are several ways a user can interact with a computer. Not every way is equally appropriate for all situations: when typing, a keyboard is more appropriate; a mouse, on the other hand, is a better fit in case the user needs to control the cursor with precision. In some complex systems, the user might need to execute several different tasks, and, therefore, might need different ways to interact with the system. In order to simplify those interactions, the use of voice commands might be a good strategy, since they often allow the user to specify the task to be executed with a richer input vocabulary than that available via other, more standard input devices. However, the development of robust speech-to-text converters (SST converters) requires a lot of time and resources which development teams often do not have. There are widely-used SST converters available on the internet, such as theWeb Speech API from Google; these systems are in a very advanced stage of maturity considering general context applications—for instance, when they are used to analyze terms and words that occur in day-to-day conversations. However, these systems are often not efficient when used to analyze contextspecific terms, which occur only in particular systems or applications. Furthermore, these systems are usually black-box and cannot be modified or improved by developers who wish to use them to solve particular specialized speech-to-text problems. To analyze possible solutions to this problem, we study the development of an additional layer of software, trained via machine learning techniques, to correct or adapt the imperfect translations generated by a black-box STT when applied to a specific domain. In particular, we propose and evaluate several machine learning solutions to improve a complex flight tickets management system to which we wish to add voice-control capabilities. In the first part of this work, we discuss our motivation and describe the domain where the proposed methods evaluated. After that, mathematical theoretical background is presented and we introduce possible solutions to the particular domain at hand. At the end, a critical analysis of the results is made and future work is discussed. |
id |
UFRGS-2_2b4e9ec67b0cbbfd007cfcefa4d2fdd5 |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/147632 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Schwade, Guilherme VieiraSilva, Bruno Castro da2016-08-25T02:16:26Z2016http://hdl.handle.net/10183/147632000999675There are several ways a user can interact with a computer. Not every way is equally appropriate for all situations: when typing, a keyboard is more appropriate; a mouse, on the other hand, is a better fit in case the user needs to control the cursor with precision. In some complex systems, the user might need to execute several different tasks, and, therefore, might need different ways to interact with the system. In order to simplify those interactions, the use of voice commands might be a good strategy, since they often allow the user to specify the task to be executed with a richer input vocabulary than that available via other, more standard input devices. However, the development of robust speech-to-text converters (SST converters) requires a lot of time and resources which development teams often do not have. There are widely-used SST converters available on the internet, such as theWeb Speech API from Google; these systems are in a very advanced stage of maturity considering general context applications—for instance, when they are used to analyze terms and words that occur in day-to-day conversations. However, these systems are often not efficient when used to analyze contextspecific terms, which occur only in particular systems or applications. Furthermore, these systems are usually black-box and cannot be modified or improved by developers who wish to use them to solve particular specialized speech-to-text problems. To analyze possible solutions to this problem, we study the development of an additional layer of software, trained via machine learning techniques, to correct or adapt the imperfect translations generated by a black-box STT when applied to a specific domain. In particular, we propose and evaluate several machine learning solutions to improve a complex flight tickets management system to which we wish to add voice-control capabilities. In the first part of this work, we discuss our motivation and describe the domain where the proposed methods evaluated. After that, mathematical theoretical background is presented and we introduce possible solutions to the particular domain at hand. At the end, a critical analysis of the results is made and future work is discussed.application/pdfengReconhecimento : PadroesAprendizagem : MaquinaSpeech RecognitionMachine learningLevenshtein distancePhonetic algorithmImproving black-box speech-to-text systems via machine learning techniquesinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bachelorThesisUniversidade Federal do Rio Grande do SulInstituto de InformáticaPorto Alegre, BR-RS2016Ciência da Computação: Ênfase em Ciência da Computação: Bachareladograduaçãoinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSORIGINAL000999675.pdf000999675.pdfTexto completo (inglês)application/pdf1489820http://www.lume.ufrgs.br/bitstream/10183/147632/1/000999675.pdf281646cc7e2781cd6d2ab586148f08f4MD51TEXT000999675.pdf.txt000999675.pdf.txtExtracted Texttext/plain116013http://www.lume.ufrgs.br/bitstream/10183/147632/2/000999675.pdf.txt8370f763cb9336bed074ff6025005ebcMD52THUMBNAIL000999675.pdf.jpg000999675.pdf.jpgGenerated Thumbnailimage/jpeg1048http://www.lume.ufrgs.br/bitstream/10183/147632/3/000999675.pdf.jpg621a53dd80a26c8921bd2056d64f58d6MD5310183/1476322018-10-29 08:40:57.214oai:www.lume.ufrgs.br:10183/147632Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2018-10-29T11:40:57Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Improving black-box speech-to-text systems via machine learning techniques |
title |
Improving black-box speech-to-text systems via machine learning techniques |
spellingShingle |
Improving black-box speech-to-text systems via machine learning techniques Schwade, Guilherme Vieira Reconhecimento : Padroes Aprendizagem : Maquina Speech Recognition Machine learning Levenshtein distance Phonetic algorithm |
title_short |
Improving black-box speech-to-text systems via machine learning techniques |
title_full |
Improving black-box speech-to-text systems via machine learning techniques |
title_fullStr |
Improving black-box speech-to-text systems via machine learning techniques |
title_full_unstemmed |
Improving black-box speech-to-text systems via machine learning techniques |
title_sort |
Improving black-box speech-to-text systems via machine learning techniques |
author |
Schwade, Guilherme Vieira |
author_facet |
Schwade, Guilherme Vieira |
author_role |
author |
dc.contributor.author.fl_str_mv |
Schwade, Guilherme Vieira |
dc.contributor.advisor1.fl_str_mv |
Silva, Bruno Castro da |
contributor_str_mv |
Silva, Bruno Castro da |
dc.subject.por.fl_str_mv |
Reconhecimento : Padroes Aprendizagem : Maquina |
topic |
Reconhecimento : Padroes Aprendizagem : Maquina Speech Recognition Machine learning Levenshtein distance Phonetic algorithm |
dc.subject.eng.fl_str_mv |
Speech Recognition Machine learning Levenshtein distance Phonetic algorithm |
description |
There are several ways a user can interact with a computer. Not every way is equally appropriate for all situations: when typing, a keyboard is more appropriate; a mouse, on the other hand, is a better fit in case the user needs to control the cursor with precision. In some complex systems, the user might need to execute several different tasks, and, therefore, might need different ways to interact with the system. In order to simplify those interactions, the use of voice commands might be a good strategy, since they often allow the user to specify the task to be executed with a richer input vocabulary than that available via other, more standard input devices. However, the development of robust speech-to-text converters (SST converters) requires a lot of time and resources which development teams often do not have. There are widely-used SST converters available on the internet, such as theWeb Speech API from Google; these systems are in a very advanced stage of maturity considering general context applications—for instance, when they are used to analyze terms and words that occur in day-to-day conversations. However, these systems are often not efficient when used to analyze contextspecific terms, which occur only in particular systems or applications. Furthermore, these systems are usually black-box and cannot be modified or improved by developers who wish to use them to solve particular specialized speech-to-text problems. To analyze possible solutions to this problem, we study the development of an additional layer of software, trained via machine learning techniques, to correct or adapt the imperfect translations generated by a black-box STT when applied to a specific domain. In particular, we propose and evaluate several machine learning solutions to improve a complex flight tickets management system to which we wish to add voice-control capabilities. In the first part of this work, we discuss our motivation and describe the domain where the proposed methods evaluated. After that, mathematical theoretical background is presented and we introduce possible solutions to the particular domain at hand. At the end, a critical analysis of the results is made and future work is discussed. |
publishDate |
2016 |
dc.date.accessioned.fl_str_mv |
2016-08-25T02:16:26Z |
dc.date.issued.fl_str_mv |
2016 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
format |
bachelorThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/147632 |
dc.identifier.nrb.pt_BR.fl_str_mv |
000999675 |
url |
http://hdl.handle.net/10183/147632 |
identifier_str_mv |
000999675 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/147632/1/000999675.pdf http://www.lume.ufrgs.br/bitstream/10183/147632/2/000999675.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/147632/3/000999675.pdf.jpg |
bitstream.checksum.fl_str_mv |
281646cc7e2781cd6d2ab586148f08f4 8370f763cb9336bed074ff6025005ebc 621a53dd80a26c8921bd2056d64f58d6 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1798486851991896064 |