{"id":"https://openalex.org/W2072229047","doi":"https://doi.org/10.1109/iscslp.2012.6423490","title":"Keyword-specific normalization based keyword spotting for spontaneous speech","display_name":"Keyword-specific normalization based keyword spotting for spontaneous speech","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2072229047","doi":"https://doi.org/10.1109/iscslp.2012.6423490","mag":"2072229047"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","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/A5100444148","display_name":"Weifeng Li","orcid":"https://orcid.org/0000-0002-1410-8966"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weifeng Li","raw_affiliation_strings":["Department of Electronic Engineering/Graduate School at Shenzhen, Tsinghua University, China","[Department of Electronic Engineering, Graduate School at Shenzhen, Tsinghua University, China]"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering/Graduate School at Shenzhen, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"[Department of Electronic Engineering, Graduate School at Shenzhen, Tsinghua University, China]","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009239895","display_name":"Qingmin Liao","orcid":"https://orcid.org/0000-0002-7509-3964"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingmin Liao","raw_affiliation_strings":["Department of Electronic Engineering/Graduate School at Shenzhen, Tsinghua University, China","[Department of Electronic Engineering, Graduate School at Shenzhen, Tsinghua University, China]"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering/Graduate School at Shenzhen, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"[Department of Electronic Engineering, Graduate School at Shenzhen, Tsinghua University, China]","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100444148"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8563,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79287919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"233","last_page":"237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/keyword-spotting","display_name":"Keyword spotting","score":0.9479174613952637},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8266782760620117},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7976932525634766},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7839075326919556},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6686713099479675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6453397274017334},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6336055397987366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5934516787528992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5586110353469849},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4195290505886078}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9479174613952637},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8266782760620117},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7976932525634766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839075326919556},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6686713099479675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6453397274017334},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6336055397987366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5934516787528992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5586110353469849},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4195290505886078},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1604474292","https://openalex.org/W1815165135","https://openalex.org/W1984514442","https://openalex.org/W2041823554","https://openalex.org/W2120097768","https://openalex.org/W2139106564","https://openalex.org/W2145978959","https://openalex.org/W2151244813","https://openalex.org/W2159377400","https://openalex.org/W2166637769","https://openalex.org/W6635848222","https://openalex.org/W6638352220","https://openalex.org/W6684440257"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2088615611"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,19,27],"novel":[4],"architecture":[5,31],"for":[6],"keyword":[7,14,79],"spotting":[8,80],"in":[9,12,103],"spontaneous":[10],"speech,":[11],"which":[13],"model":[15,66,75],"is":[16,72],"trained":[17],"from":[18],"small":[20],"number":[21],"of":[22,85,105],"acoustic":[23],"examples":[24],"provided":[25],"by":[26,40],"user.":[28],"The":[29],"word-spotting":[30],"relies":[32],"on":[33],"scoring":[34],"patch":[35],"feature":[36],"vector":[37],"sequences":[38],"extracted":[39],"using":[41],"sliding":[42],"windows,":[43],"and":[44,48,58,69],"performing":[45],"keyword-specific":[46],"normalization":[47],"threshold":[49],"setting.":[50],"Dynamic":[51],"time":[52],"warping":[53],"(DTW)":[54],"based":[55,96],"template":[56],"matching":[57],"Gaussian":[59],"Mixture":[60],"Models":[61],"(GMM)":[62],"are":[63],"proposed":[64,73,87,92],"to":[65,74,109],"the":[67,76,83,86,91,110],"keyword,":[68],"another":[70],"GMM":[71,93],"non-keywords.":[77],"Our":[78],"experiments":[81],"demonstrate":[82],"effectiveness":[84],"methods.":[88],"More":[89],"specifically,":[90],"log-likelihood":[94],"ratio":[95],"method":[97],"achieves":[98],"about":[99],"17%":[100],"absolute":[101],"improvement":[102],"terms":[104],"recall":[106],"rates":[107],"compared":[108],"baseline":[111],"system.":[112]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
