{"id":"https://openalex.org/W3121474641","doi":null,"title":"Training Noise-Robust Spoken Phrase Detectors with Scarce and Private Data: An Application to Classroom Observation Videos","display_name":"Training Noise-Robust Spoken Phrase Detectors with Scarce and Private Data: An Application to Classroom Observation Videos","publication_year":2019,"publication_date":"2019-04-24","ids":{"openalex":"https://openalex.org/W3121474641","mag":"3121474641"},"language":"en","primary_location":{"id":"pmh:oai:digitalcommons.wpi.edu:etd-theses-2288","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.wpi.edu/etd-theses/1289","pdf_url":"http://digital.wpi.edu/downloads/6t053j49t","source":{"id":"https://openalex.org/S4377196141","display_name":"Digital WPI","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Masters Theses (All Theses, All Years)","raw_type":"text"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://digital.wpi.edu/downloads/6t053j49t","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026409040","display_name":"Brian Zylich","orcid":"https://orcid.org/0000-0001-5223-8780","observed_orcids":["https://orcid.org/0000-0001-5223-8780"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Brian Zylich","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5223-8780","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5026409040"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9437999725341797,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9437999725341797,"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":0.03280000016093254,"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/T10860","display_name":"Speech and Audio Processing","score":0.019899999722838402,"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/noise-robust-speech-recognition","display_name":"noise-robust speech recognition","score":0.7950000166893005},{"id":"https://openalex.org/keywords/polite-language","display_name":"polite language","score":0.7670000195503235},{"id":"https://openalex.org/keywords/data-privacy","display_name":"data privacy","score":0.7120000123977661},{"id":"https://openalex.org/keywords/audio-data-augmentation","display_name":"audio data augmentation","score":0.6520000100135803},{"id":"https://openalex.org/keywords/sound-synthesis","display_name":"sound synthesis","score":0.7710000276565552},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.9369999766349792},{"id":"https://openalex.org/keywords/teacher-language-use","display_name":"teacher language","score":0.42500001192092896}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6439293026924133},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5929927825927734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5703993439674377},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5240947604179382},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49765852093696594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4808650612831116},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44212672114372253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40871503949165344},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3335909843444824},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0968782901763916},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:digitalcommons.wpi.edu:etd-theses-2288","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.wpi.edu/etd-theses/1289","pdf_url":"http://digital.wpi.edu/downloads/6t053j49t","source":{"id":"https://openalex.org/S4377196141","display_name":"Digital WPI","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Masters Theses (All Theses, All Years)","raw_type":"text"},{"id":"mag:3121474641","doi":null,"is_oa":false,"landing_page_url":"https://digitalcommons.wpi.edu/etd-theses/1289/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:digitalcommons.wpi.edu:etd-theses-2288","doi":null,"is_oa":true,"landing_page_url":"https://digitalcommons.wpi.edu/etd-theses/1289","pdf_url":"http://digital.wpi.edu/downloads/6t053j49t","source":{"id":"https://openalex.org/S4377196141","display_name":"Digital WPI","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Masters Theses (All Theses, All Years)","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.4156000018119812}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3121474641.pdf","grobid_xml":"https://content.openalex.org/works/W3121474641.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W657812159","https://openalex.org/W1560013842","https://openalex.org/W1600744878","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1979651826","https://openalex.org/W1993882792","https://openalex.org/W2075997786","https://openalex.org/W2099621636","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2115630042","https://openalex.org/W2164931619","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2294813873","https://openalex.org/W2311973309","https://openalex.org/W2339391301","https://openalex.org/W2399733683","https://openalex.org/W2401567014","https://openalex.org/W2515753980","https://openalex.org/W2548272333","https://openalex.org/W2593910181","https://openalex.org/W2618099328","https://openalex.org/W2626778328","https://openalex.org/W2763188033","https://openalex.org/W2773005317","https://openalex.org/W2797187289","https://openalex.org/W2801798988","https://openalex.org/W2884254529","https://openalex.org/W2894479865","https://openalex.org/W2913340405","https://openalex.org/W2949117887","https://openalex.org/W2949650786","https://openalex.org/W2950051476","https://openalex.org/W2957865981"],"related_works":["https://openalex.org/W3015944914","https://openalex.org/W2965397554","https://openalex.org/W4367022905","https://openalex.org/W7222069053","https://openalex.org/W7221756989","https://openalex.org/W4245224207","https://openalex.org/W3189585926","https://openalex.org/W2973538113","https://openalex.org/W3097352614","https://openalex.org/W2398529454"],"abstract_inverted_index":{"We":[0,153],"explore":[1,207],"how":[2],"to":[3,58,164,199,209,217,249],"automatically":[4],"detect":[5],"specific":[6],"phrases":[7,62,163],"in":[8,42,86,185],"audio":[9,214],"from":[10,131],"noisy,":[11],"multi-speaker":[12],"videos":[13,24,130,143],"using":[14,123,229],"deep":[15],"neural":[16,192],"networks.":[17],"Specifically,":[18],"we":[19,115,175,189,206,236],"focus":[20],"on":[21],"classroom":[22,87,129,141,186],"observation":[23,88,142],"that":[25],"contain":[26],"a":[27,124,136,177,191],"few":[28],"adult":[29],"teachers":[30,248],"and":[31,70,117,201,204,212,223,243,246],"several":[32],"small":[33],"children":[34],"(<":[35],"5":[36],"years":[37],"old).":[38],"At":[39],"any":[40],"point":[41],"these":[43],"videos,":[44,187],"multiple":[45],"people":[46],"may":[47],"be":[48],"talking,":[49],"shouting,":[50],"crying,":[51],"or":[52],"singing":[53],"simultaneously.":[54],"Our":[55,169],"goal":[56],"is":[57,79],"recognize":[59],"polite":[60,161,232,241,254],"speech":[61,78,99,162,183,196,233,242],"such":[63,77,102],"as":[64,73,103,133,135],"\"Good":[65],"job\",":[66],"\"Thank":[67],"you\",":[68],"\"Please\",":[69],"\"You're":[71],"welcome\",":[72],"the":[74,82,91,149,172,219,225,238],"occurrence":[75],"of":[76,81,110,126,139,151,160,253],"one":[80],"behavioral":[83],"markers":[84],"used":[85],"coding":[89],"via":[90],"Classroom":[92],"Assessment":[93],"Scoring":[94],"System":[95],"(CLASS)":[96],"protocol.":[97],"Commercial":[98],"recognition":[100],"services":[101],"Google":[104],"Cloud":[105],"Speech":[106],"are":[107,171],"impractical":[108],"because":[109],"data":[111],"privacy":[112],"concerns.":[113],"Therefore,":[114],"train":[116],"test":[118],"our":[119,146,166,230],"own":[120],"custom":[121],"models":[122],"combination":[125],"publicly":[127],"available":[128],"YouTube,":[132],"well":[134],"private":[137],"dataset":[138],"real":[140],"collected":[144],"by":[145],"colleagues":[147],"at":[148],"University":[150],"Virginia.":[152],"also":[154],"crowdsource":[155],"an":[156],"additional":[157],"1152":[158],"recordings":[159],"augment":[165],"training":[167,220],"dataset.":[168],"contributions":[170],"following:":[173],"(1)":[174],"design":[176],"crowdsourcing":[178],"task":[179],"for":[180,195],"efficiently":[181],"labeling":[182],"events":[184],"(2)":[188],"develop":[190],"network-based":[193],"architecture":[194],"recognition,":[197],"robust":[198],"noise":[200],"overlapping":[202],"speech,":[203],"(3)":[205],"methods":[208],"synthesize":[210],"new":[211],"authentic":[213],"data,":[215],"both":[216],"increase":[218],"set":[221],"size":[222],"reduce":[224],"class":[226],"imbalance.":[227],"Finally,":[228],"trained":[231],"detector,":[234],"(4)":[235],"investigate":[237],"relationship":[239],"between":[240],"CLASS":[244],"scores":[245],"enable":[247],"visualize":[250],"their":[251],"use":[252],"language.":[255]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-02-01T00:00:00"}