{"id":"https://openalex.org/W2773005317","doi":"https://doi.org/10.1109/roman.2017.8172449","title":"Exploring data augmentation methods in reverberant human-robot voice communication","display_name":"Exploring data augmentation methods in reverberant human-robot voice communication","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2773005317","doi":"https://doi.org/10.1109/roman.2017.8172449","mag":"2773005317"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2017.8172449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2017.8172449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","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/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Honda Research Institute Japan Ltd. Co., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049329632","display_name":"Keisuke Nakamura","orcid":"https://orcid.org/0000-0002-4979-2083"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Nakamura","raw_affiliation_strings":["Honda Research Institute Japan Ltd. Co., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Ltd. Co., Japan","institution_ids":["https://openalex.org/I1283473643"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283473643"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1154","last_page":"1158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8393319845199585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7940696477890015},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.637380838394165},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5910592675209045},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.572530210018158},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5396660566329956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5131643414497375},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4718480110168457},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.45504629611968994},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4204868674278259},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4134982228279114},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3669472336769104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1358151137828827}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8393319845199585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940696477890015},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.637380838394165},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5910592675209045},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.572530210018158},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5396660566329956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131643414497375},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4718480110168457},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.45504629611968994},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4204868674278259},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4134982228279114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3669472336769104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1358151137828827},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/roman.2017.8172449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2017.8172449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1508165687","https://openalex.org/W1509793305","https://openalex.org/W1973125743","https://openalex.org/W1979651826","https://openalex.org/W1987900425","https://openalex.org/W1989314204","https://openalex.org/W2009106392","https://openalex.org/W2099621636","https://openalex.org/W2117678320","https://openalex.org/W2398723458","https://openalex.org/W2407080277","https://openalex.org/W2510616059","https://openalex.org/W2696967604","https://openalex.org/W2970850616","https://openalex.org/W6675409298","https://openalex.org/W6713072105","https://openalex.org/W6713762819"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2924917467","https://openalex.org/W3195353062","https://openalex.org/W2099731689","https://openalex.org/W3186268266"],"abstract_inverted_index":{"Collecting":[0],"training":[1],"data":[2,22,54,113,116,129],"is":[3,26,36],"not":[4],"an":[5],"easy":[6],"task":[7],"especially":[8],"in":[9,57,70,130],"situation":[10],"involving":[11],"robots":[12],"that":[13,109],"require":[14],"tremendous":[15],"physical":[16],"effort.":[17],"The":[18],"ability":[19],"to":[20,30,38,64],"augment":[21],"through":[23],"synthetic":[24],"means":[25],"a":[27,62,71,131],"convenient":[28],"tool":[29],"solve":[31],"this":[32,49],"problem.":[33],"Therefore":[34],"it":[35],"important":[37],"evaluate":[39],"the":[40,43,79,95,110],"extent":[41],"of":[42,45,112],"usefulness":[44],"augmented":[46],"data.":[47,67],"In":[48,122],"paper,":[50],"we":[51,125],"will":[52],"explore":[53],"augmentation":[55,114],"schemes":[56],"reverberant":[58,73,132],"environment":[59,74],"and":[60,76,94,115],"investigate":[61,77],"method":[63],"effectively":[65],"select":[66],"We":[68],"experiment":[69],"real":[72,127],"condition":[75],"both":[78],"traditional":[80],"automatic":[81],"speech":[82],"recognition":[83],"(ASR)":[84],"system":[85,98,120],"based":[86,99],"on":[87,100],"gaussian":[88],"mixture":[89],"model-hidden":[90],"markov":[91],"model":[92],"(GMM-HMM)":[93],"most":[96],"current":[97],"Deep":[101],"Neural":[102],"Networks":[103],"(i.e,":[104],"HMM-DNN).":[105],"Our":[106],"results":[107],"show":[108],"combination":[111],"selection,":[117],"further":[118],"improves":[119],"performance.":[121],"our":[123],"experiments,":[124],"used":[126],"test":[128],"hands-free":[133],"human-robot":[134],"communication":[135],"scenario.":[136]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}