{"id":"https://openalex.org/W2396587823","doi":"https://doi.org/10.1109/icassp.2016.7472835","title":"Approximate search of audio queries by using DTW with phone time boundary and data augmentation","display_name":"Approximate search of audio queries by using DTW with phone time boundary and data augmentation","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2396587823","doi":"https://doi.org/10.1109/icassp.2016.7472835","mag":"2396587823"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5075575823","display_name":"Haikua Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Haikua Xu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018722799","display_name":"Jingyong Hou","orcid":"https://orcid.org/0000-0002-1861-7776"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyong Hou","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, Shaanxi, CN"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, Shaanxi, CN","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046222772","display_name":"Van Tung Pham","orcid":"https://orcid.org/0000-0002-2103-1901"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Van Tung Pham","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113828649","display_name":"Cheung-Chi Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheung-Chi Leung","raw_affiliation_strings":["Agency for Science Technology and Research, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Agency for Science Technology and Research, Singapore, SG","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107094040","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0001-8085-2374"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Agency for Science Technology and Research, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Agency for Science Technology and Research, Singapore, SG","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051897589","display_name":"Van Hai","orcid":"https://orcid.org/0000-0002-9554-5171"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Van Hai Do","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751610","display_name":"Hang Lv","orcid":"https://orcid.org/0000-0003-3761-1684"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Lv","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, Shaanxi, CN"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, Shaanxi, CN","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, Shaanxi, CN"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, Shaanxi, CN","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Agency for Science Technology and Research, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Agency for Science Technology and Research, Singapore, SG","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore, SG","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5075575823"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.5218,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90020245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6030","last_page":"6034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9980000257492065,"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":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.7858489751815796},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7006188035011292},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4142727553844452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4044433534145355},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3297455310821533},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10181975364685059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858489751815796},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7006188035011292},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4142727553844452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4044433534145355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3297455310821533},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10181975364685059},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W103757200","https://openalex.org/W1524333225","https://openalex.org/W1567520911","https://openalex.org/W1580290522","https://openalex.org/W1979459060","https://openalex.org/W2085628288","https://openalex.org/W2094721296","https://openalex.org/W2104283211","https://openalex.org/W2117678320","https://openalex.org/W2131342762","https://openalex.org/W2137044559","https://openalex.org/W2171019095","https://openalex.org/W2295327090","https://openalex.org/W2399363370","https://openalex.org/W2401805659","https://openalex.org/W2402401665","https://openalex.org/W2442329935","https://openalex.org/W2915397826","https://openalex.org/W2916450621","https://openalex.org/W4231856373","https://openalex.org/W4240592325","https://openalex.org/W6631362777","https://openalex.org/W6713061419","https://openalex.org/W6718561954","https://openalex.org/W6758788767","https://openalex.org/W6759411180","https://openalex.org/W6813611564"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Dynamic":[0],"Time":[1],"Warping":[2],"(DTW)":[3],"is":[4,34,46,104,110],"widely":[5],"used":[6],"in":[7],"language":[8],"independent":[9],"query-by-example":[10],"(QbE)":[11],"spoken":[12],"term":[13],"detection":[14],"(STD)":[15],"tasks":[16],"due":[17],"to":[18,37,48,118],"its":[19],"high":[20],"performance.":[21],"However,":[22],"there":[23],"are":[24,144],"two":[25],"limitations":[26],"of":[27,41,51,88,99,132],"DTW":[28,45],"based":[29],"template":[30,70],"matching,":[31],"1)":[32],"it":[33],"not":[35],"straightforward":[36],"perform":[38],"approximate":[39,64],"match":[40],"audio":[42,89],"queries;":[43],"2)":[44],"sensitive":[47],"the":[49,55,58,97,119,130,133,139],"mismatch":[50],"signal":[52],"conditions":[53],"between":[54],"query":[56],"and":[57,115,141,149],"speech":[59],"search":[60,142],"data.":[61,122],"To":[62,83],"allow":[63],"search,":[65],"we":[66,91],"propose":[67],"a":[68,80],"partial":[69],"matching":[71],"strategy":[72],"using":[73],"phone":[74,81],"time":[75],"boundary":[76],"information":[77],"generated":[78,111],"by":[79,112,147],"recognizer.":[82],"have":[84],"more":[85],"invariant":[86],"representation":[87],"signals,":[90],"use":[92],"bottleneck":[93],"features":[94],"(BNF)":[95],"as":[96],"input":[98],"DTW.":[100],"The":[101],"BNF":[102],"network":[103],"trained":[105],"from":[106],"augmented":[107],"data,":[108],"which":[109],"adding":[113],"reverberation":[114,148],"additive":[116],"noises":[117],"clean":[120],"training":[121],"Experimental":[123],"results":[124],"on":[125],"QUESST":[126],"2015":[127],"task":[128],"shows":[129],"effectiveness":[131],"proposed":[134],"methods":[135],"for":[136],"QbE-STD":[137],"when":[138],"queries":[140],"data":[143],"both":[145],"distorted":[146],"noises.":[150]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}