{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/14720"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/14720","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Surface electromyography based speech recognition system and development toolkit","abstract":"This thesis describes the implementation of an automatic speech recognition system based on surface electromyography signals. Data collection was done using a bipolar electrode configuration with a sampling rate of 5.77 kHz. Four feature sets, the short-time Fourier transform (STFT), the dual-tree complex wavelet transform (DTCWT), a non-causal time-domain based (E4-NC), and a causal version of E4-NC (E4-C) were implemented. Classification was performed using a hidden Markov model (HMM). The system implemented was able to achieve an accuracy rate of 74.24% with E4-NC and 61.25% with E4-C. These results are comparable to previously reported results for offline, single session, isolated word recognition. Additional testing was performed on five subjects using E4-C and yielded accuracy rates ranging from 51.8% to 81.88% with an average accuracy rate of 64.9% during offline, single session, isolated word recognition. The E4-C was chosen since it offered the best performance among the causal feature sets and non-causal feature sets cannot be used with real-time online classification. Online classification capabilities were implemented and simulations using the confidence interval (CI) and minimum noise likelihood (MNL) decision rubrics yielded accuracy rates of 77.5% and 72.5%, respectively, during online, single session, isolated word recognition.","abstract_html":"This thesis describes the implementation of an automatic speech recognition system based on surface electromyography signals. Data collection was done using a bipolar electrode configuration with a sampling rate of 5.77 kHz. Four feature sets, the short-time Fourier transform (STFT), the dual-tree complex wavelet transform (DTCWT), a non-causal time-domain based (E4-NC), and a causal version of E4-NC (E4-C) were implemented. Classification was performed using a hidden Markov model (HMM). The system implemented was able to achieve an accuracy rate of 74.24% with E4-NC and 61.25% with E4-C. These results are comparable to previously reported results for offline, single session, isolated word recognition. Additional testing was performed on five subjects using E4-C and yielded accuracy rates ranging from 51.8% to 81.88% with an average accuracy rate of 64.9% during offline, single session, isolated word recognition. The E4-C was chosen since it offered the best performance among the causal feature sets and non-causal feature sets cannot be used with real-time online classification. Online classification capabilities were implemented and simulations using the confidence interval (CI) and minimum noise likelihood (MNL) decision rubrics yielded accuracy rates of 77.5% and 72.5%, respectively, during online, single session, isolated word recognition.","abstract_has_math":false,"creators":["Chang, Daniel"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Bretl, Timothy W."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010-01-06T16:41:53Z","date_published":"2010-01-06T16:41:53Z","updated_at":"2026-07-22T22:25:08Z","subjects":["sEMG","speech recognition","surface electromyography"],"languages":["en"],"rights":["Copyright 2009 Daniel Chang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/14720","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Bretl, Timothy W."]},{"key":"dc:creator","label":"Author","values":["Chang, Daniel"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2010-01-06T16:41:53Z","2012-01-07T11:00:08Z","2009-12"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["sEMG","speech recognition","surface electromyography"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2009 Daniel Chang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/14720"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This thesis describes the implementation of an automatic speech recognition system based on surface electromyography signals. Data collection was done using a bipolar electrode configuration with a sampling rate of 5.77 kHz. Four feature sets, the short-time Fourier transform (STFT), the dual-tree complex wavelet transform (DTCWT), a non-causal time-domain based (E4-NC), and a causal version of E4-NC (E4-C) were implemented. Classification was performed using a hidden Markov model (HMM). The system implemented was able to achieve an accuracy rate of 74.24% with E4-NC and 61.25% with E4-C. These results are comparable to previously reported results for offline, single session, isolated word recognition. Additional testing was performed on five subjects using E4-C and yielded accuracy rates ranging from 51.8% to 81.88% with an average accuracy rate of 64.9% during offline, single session, isolated word recognition. The E4-C was chosen since it offered the best performance among the causal feature sets and non-causal feature sets cannot be used with real-time online classification. Online classification capabilities were implemented and simulations using the confidence interval (CI) and minimum noise likelihood (MNL) decision rubrics yielded accuracy rates of 77.5% and 72.5%, respectively, during online, single session, isolated word recognition.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2009-10-20T20:14:47Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 Chang_Daniel.pdf: 953971 bytes, checksum: a3723920c553584df11b6a08df773e7a (MD5) Chang_Daniel.doc: 1249792 bytes, checksum: 1f1b649be6533c6d549c242f9c602a6a (MD5)","Made available in DSpace on 2010-01-06T16:41:53Z (GMT). No. of bitstreams: 3 license.txt: 4061 bytes, checksum: 85bfad10e88267eb3a795131cf94a52c (MD5) Chang_Daniel.pdf: 953971 bytes, checksum: a3723920c553584df11b6a08df773e7a (MD5) Chang_Daniel.doc: 1249792 bytes, checksum: 1f1b649be6533c6d549c242f9c602a6a (MD5)","Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by William Ingram (wingram2@illinois.edu) on 2010-01-06T16:42:21Z Item is restricted until 2012-01-06T16:42:19Z","Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2012-01-07T11:00:08Z Item was in collections: Dissertations and Theses - Electrical and Computer Engineering (ID: 446) University of Illinois Dissertations and Theses (ID: 204) No. of bitstreams: 4 license.txt: 4061 bytes, checksum: 85bfad10e88267eb3a795131cf94a52c (MD5) Chang_Daniel.pdf.txt: 83622 bytes, checksum: 3f7c4453b6e9ec5ec284318b4cd4e317 (MD5) Chang_Daniel.pdf: 953971 bytes, checksum: a3723920c553584df11b6a08df773e7a (MD5) Chang_Daniel.doc: 1249792 bytes, checksum: 1f1b649be6533c6d549c242f9c602a6a (MD5)","Item released from any restrictions by Sarah Shreeves (sshreeve@illinois.edu) on 2012-01-07T11:00:08Z"]},{"key":"dc:title","label":"Title","values":["Surface electromyography based speech recognition system and development toolkit"]}]}],"canonical_facts":{"dc:contributor":["Bretl, Timothy W."],"dc:creator":["Chang, Daniel"],"dc:date":["2010-01-06T16:41:53Z","2012-01-07T11:00:08Z","2009-12"],"dc:description":["This thesis describes the implementation of an automatic speech recognition system based on surface electromyography signals. Data collection was done using a bipolar electrode configuration with a sampling rate of 5.77 kHz. Four feature sets, the short-time Fourier transform (STFT), the dual-tree complex wavelet transform (DTCWT), a non-causal time-domain based (E4-NC), and a causal version of E4-NC (E4-C) were implemented. Classification was performed using a hidden Markov model (HMM). The system implemented was able to achieve an accuracy rate of 74.24% with E4-NC and 61.25% with E4-C. These results are comparable to previously reported results for offline, single session, isolated word recognition. Additional testing was performed on five subjects using E4-C and yielded accuracy rates ranging from 51.8% to 81.88% with an average accuracy rate of 64.9% during offline, single session, isolated word recognition. The E4-C was chosen since it offered the best performance among the causal feature sets and non-causal feature sets cannot be used with real-time online classification. Online classification capabilities were implemented and simulations using the confidence interval (CI) and minimum noise likelihood (MNL) decision rubrics yielded accuracy rates of 77.5% and 72.5%, respectively, during online, single session, isolated word recognition.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2009-10-20T20:14:47Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 Chang_Daniel.pdf: 953971 bytes, checksum: a3723920c553584df11b6a08df773e7a (MD5) Chang_Daniel.doc: 1249792 bytes, checksum: 1f1b649be6533c6d549c242f9c602a6a (MD5)","Made available in DSpace on 2010-01-06T16:41:53Z (GMT). No. of bitstreams: 3 license.txt: 4061 bytes, checksum: 85bfad10e88267eb3a795131cf94a52c (MD5) Chang_Daniel.pdf: 953971 bytes, checksum: a3723920c553584df11b6a08df773e7a (MD5) Chang_Daniel.doc: 1249792 bytes, checksum: 1f1b649be6533c6d549c242f9c602a6a (MD5)","Item marked as restricted to the 'UIUC Users [automated]' Group (id=2) by William Ingram (wingram2@illinois.edu) on 2010-01-06T16:42:21Z Item is restricted until 2012-01-06T16:42:19Z","Item reinstated by Sarah Shreeves (sshreeve@illinois.edu) on 2012-01-07T11:00:08Z Item was in collections: Dissertations and Theses - Electrical and Computer Engineering (ID: 446) University of Illinois Dissertations and Theses (ID: 204) No. of bitstreams: 4 license.txt: 4061 bytes, checksum: 85bfad10e88267eb3a795131cf94a52c (MD5) Chang_Daniel.pdf.txt: 83622 bytes, checksum: 3f7c4453b6e9ec5ec284318b4cd4e317 (MD5) Chang_Daniel.pdf: 953971 bytes, checksum: a3723920c553584df11b6a08df773e7a (MD5) Chang_Daniel.doc: 1249792 bytes, checksum: 1f1b649be6533c6d549c242f9c602a6a (MD5)","Item released from any restrictions by Sarah Shreeves (sshreeve@illinois.edu) on 2012-01-07T11:00:08Z"],"dc:identifier":["http://hdl.handle.net/2142/14720"],"dc:language":["en"],"dc:rights":["Copyright 2009 Daniel Chang"],"dc:subject":["sEMG","speech recognition","surface electromyography"],"dc:title":["Surface electromyography based speech recognition system and development toolkit"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:08Z"}