{"id":"https://openalex.org/W2293535060","doi":"https://doi.org/10.21437/interspeech.2014-395","title":"Recent improvements in SRI's keyword detection system for noisy audio","display_name":"Recent improvements in SRI's keyword detection system for noisy audio","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2293535060","doi":"https://doi.org/10.21437/interspeech.2014-395","mag":"2293535060"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-395","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5058481276","display_name":"Julien van Hout","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julien van Hout","raw_affiliation_strings":["SRI-International"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI-International","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060715364","display_name":"Dimitra Vergyri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitra Vergyri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025265147","display_name":"Martin Graciarena","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Graciarena","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059342552","display_name":"Arindam Mandal","orcid":"https://orcid.org/0000-0003-2804-3638"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arindam Mandal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112857367","display_name":"Horacio Franco","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Horacio Franco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9938,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75901776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1727","last_page":"1731"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9513307809829712},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8341277241706848},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6979604363441467},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5466079115867615},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5080587863922119},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4634072482585907},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46246880292892456},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44683530926704407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4439043402671814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37977299094200134},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33553773164749146},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0739666223526001}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9513307809829712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341277241706848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6979604363441467},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5466079115867615},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5080587863922119},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4634072482585907},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46246880292892456},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44683530926704407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4439043402671814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37977299094200134},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33553773164749146},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0739666223526001},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-395","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W87396816","https://openalex.org/W1582482241","https://openalex.org/W1968652492","https://openalex.org/W1981730446","https://openalex.org/W1986840384","https://openalex.org/W2023582935","https://openalex.org/W2056986588","https://openalex.org/W2075012882","https://openalex.org/W2097978681","https://openalex.org/W2103371184","https://openalex.org/W2108072369","https://openalex.org/W2114537326","https://openalex.org/W2114719288","https://openalex.org/W2130020166","https://openalex.org/W2135431242","https://openalex.org/W2140979961","https://openalex.org/W2142806759","https://openalex.org/W2151244813","https://openalex.org/W2167338739","https://openalex.org/W2295098554","https://openalex.org/W2395321025","https://openalex.org/W2397840928","https://openalex.org/W2398177287","https://openalex.org/W2400523955","https://openalex.org/W2404382759","https://openalex.org/W2405666970"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W4385352507","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4286904253","https://openalex.org/W2386245264","https://openalex.org/W4389912005","https://openalex.org/W4391021514","https://openalex.org/W2388033618","https://openalex.org/W1902557034"],"abstract_inverted_index":{"We":[0,22,99],"present":[1],"improvements":[2],"to":[3,46],"a":[4,24,60],"keyword":[5,93],"spotting":[6],"(KWS)":[7],"system":[8,25],"that":[9],"operates":[10],"in":[11],"highly":[12],"adverse":[13],"channel":[14],"conditions":[15],"with":[16],"very":[17],"low":[18],"signal-to-noise":[19],"ratio":[20],"levels.":[21],"employ":[23],"combination":[26],"approach":[27],"by":[28],"combining":[29],"the":[30,101,104],"outputs":[31],"of":[32,53,63],"multiple":[33],"large":[34],"vocabulary":[35],"continuous":[36],"speech":[37,56],"recognition":[38],"(LVCSR)":[39],"systems.":[40],"These":[41],"systems":[42],"are":[43],"complementary":[44],"thanks":[45],"different":[47],"design":[48],"decisions":[49],"across":[50],"all":[51],"levels":[52],"information:":[54],"three":[55,79],"activity":[57],"detections":[58],"systems;":[59],"wide":[61],"range":[62],"front-end":[64],"signal":[65],"processing":[66],"features":[67,74],"(standard":[68],"cepstral":[69],"and":[70,75,88,97],"filter-bank":[71],"features,":[72],"noise-robust":[73],"multi-layer":[76],"perceptron":[77],"features);":[78],"statistical":[80],"acoustic":[81],"model":[82],"types":[83],"(Gaussian":[84],"mixtures":[85],"models,":[86],"deep":[87],"convolutional":[89],"neural":[90],"networks);":[91],"two":[92],"search":[94],"strategies":[95],"(wordbased":[96],"phone-based).":[98],"explore":[100],"scenario":[102],"where":[103]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
