{"id":"https://openalex.org/W2593268422","doi":"https://doi.org/10.1109/iscslp.2016.7918434","title":"Comparison of DCT and autoencoder-based features for DNN-HMM multimodal silent speech recognition","display_name":"Comparison of DCT and autoencoder-based features for DNN-HMM multimodal silent speech recognition","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2593268422","doi":"https://doi.org/10.1109/iscslp.2016.7918434","mag":"2593268422"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101436881","display_name":"Licheng Liu","orcid":"https://orcid.org/0000-0003-4891-9211"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Licheng Liu","raw_affiliation_strings":["School of Computer Science and Technology, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113123753","display_name":"Yan Ji","orcid":"https://orcid.org/0000-0002-9214-5463"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Ji","raw_affiliation_strings":["School of Computer Science and Technology, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102767807","display_name":"Hongcui Wang","orcid":"https://orcid.org/0009-0002-9492-0934"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongcui Wang","raw_affiliation_strings":["School of Computer Science and Technology, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University","institution_ids":["https://openalex.org/I132369690"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029785566","display_name":"B. Denby","orcid":"https://orcid.org/0000-0003-4572-1656"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bruce Denby","raw_affiliation_strings":["School of Computer Science and Technology, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University","institution_ids":["https://openalex.org/I132369690"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I132369690"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8570899963378906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8314923644065857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7607488632202148},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.715753972530365},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.6052452325820923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5473563075065613},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5138955116271973},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48145145177841187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4500378966331482},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4400518834590912},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.43376290798187256},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.410381942987442},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07956516742706299}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8570899963378906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8314923644065857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7607488632202148},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.715753972530365},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.6052452325820923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5473563075065613},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5138955116271973},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48145145177841187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4500378966331482},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4400518834590912},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.43376290798187256},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.410381942987442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07956516742706299},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918434","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327240","display_name":"Liga Portuguesa Contra o Cancro","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W112026838","https://openalex.org/W144370208","https://openalex.org/W1916685473","https://openalex.org/W2008120082","https://openalex.org/W2394559107","https://openalex.org/W2556403182","https://openalex.org/W2739718343","https://openalex.org/W3127686677","https://openalex.org/W4296769569","https://openalex.org/W6601785968","https://openalex.org/W6604549823"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"Hidden":[0],"Markov":[1,7],"Model":[2,8],"and":[3,28,105],"Deep":[4,29,91],"Neural":[5],"Network-Hidden":[6],"speech":[9,20,79,103,114,120],"recognition":[10,104,115,121],"performance":[11,59,116],"for":[12,61,85,101,106,117],"a":[13,34,69],"portable":[14],"ultrasound":[15],"+":[16],"video":[17],"multimodal":[18,77],"silent":[19,78,109,113,119],"interface":[21],"is":[22,82],"investigated":[23],"using":[24],"Discrete":[25],"Cosine":[26],"Transform":[27],"Auto":[30],"Encoder-based":[31],"features":[32,46,56],"with":[33],"range":[35],"of":[36,45,73],"dimensionalities.":[37],"Experimental":[38],"results":[39],"show":[40],"that":[41,53,89],"the":[42,54,74,86,90,112],"two":[43],"types":[44],"achieve":[47],"similar":[48],"Word":[49],"Error":[50],"Rate,":[51],"but":[52],"autoencoder":[55],"maintain":[57],"good":[58],"even":[60],"very":[62,70],"low-dimension":[63],"feature":[64],"vectors,":[65],"demonstrating":[66],"potential":[67],"as":[68,122],"compact":[71],"representation":[72],"information":[75],"in":[76],"data.":[80],"It":[81],"also":[83],"shown":[84],"first":[87],"time":[88],"Network/Markov":[92],"approach,":[93],"which":[94],"has":[95],"been":[96],"demonstrated":[97],"to":[98],"be":[99],"beneficial":[100],"acoustic":[102],"articulatory":[107],"sensor-based":[108],"speech,":[110],"improves":[111],"video-based":[118],"well.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}