{"id":"https://openalex.org/W4385823483","doi":"https://doi.org/10.21437/interspeech.2023-597","title":"PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords","display_name":"PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823483","doi":"https://doi.org/10.21437/interspeech.2023-597"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-597","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.16511","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030203043","display_name":"Yong-Hyeok Lee","orcid":"https://orcid.org/0000-0002-2972-9474"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yong-Hyeok Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020960851","display_name":"Nam Hyun Cho","orcid":"https://orcid.org/0000-0002-7188-0565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Namhyun Cho","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030203043"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4105,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93891776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3964","last_page":"3968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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":0.9950000047683716,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9883000254631042,"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/T10028","display_name":"Topic Modeling","score":0.9848999977111816,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.9111096262931824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8518791794776917},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6515176892280579},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.642536997795105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6331560015678406},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.619627058506012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4933256208896637},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4902392029762268},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48780587315559387},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4158018231391907}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9111096262931824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518791794776917},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6515176892280579},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.642536997795105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6331560015678406},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.619627058506012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4933256208896637},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4902392029762268},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48780587315559387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4158018231391907},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-597","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.16511","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.16511","pdf_url":"https://arxiv.org/pdf/2308.16511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.16511","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.16511","pdf_url":"https://arxiv.org/pdf/2308.16511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823483.pdf","grobid_xml":"https://content.openalex.org/works/W4385823483.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"a":[3,42],"novel":[4],"zero-shot":[5],"user-defined":[6],"keyword":[7,17,79],"spotting":[8,80],"model":[9,67,71,84,118],"that":[10,25],"utilizes":[11],"the":[12,16,22,69,87],"audio-phoneme":[13],"relationship":[14],"of":[15,107,115],"to":[18],"improve":[19],"performance.":[20],"Unlike":[21],"previous":[23],"approach":[24],"estimates":[26],"at":[27,121],"utterance":[28,33],"level,":[29],"we":[30],"use":[31],"both":[32],"and":[34,50,72,89,99,109],"phoneme":[35],"level":[36],"information.":[37],"Our":[38,82],"proposed":[39,66,83,117],"method":[40],"comprises":[41],"two-stream":[43],"speech":[44],"encoder":[45],"architecture,":[46],"self-attention-based":[47],"pattern":[48],"extractor,":[49],"phoneme-level":[51],"detection":[52],"loss":[53],"for":[54],"high":[55],"performance":[56,75],"in":[57],"various":[58],"pronunciation":[59],"environments.":[60],"Based":[61],"on":[62],"experimental":[63],"results,":[64],"our":[65,116],"outperforms":[68],"baseline":[70],"achieves":[73],"competitive":[74],"compared":[76],"with":[77,102],"full-shot":[78],"models.":[81],"significantly":[85],"improves":[86],"EER":[88],"AUC":[90],"across":[91],"all":[92],"datasets,":[93],"including":[94],"familiar":[95],"words,":[96],"proper":[97],"nouns,":[98],"indistinguishable":[100],"pronunciations,":[101],"an":[103],"average":[104],"relative":[105],"improvement":[106],"67%":[108],"80%,":[110],"respectively.":[111],"The":[112],"implementation":[113],"code":[114],"is":[119],"available":[120],"https://github.com/ncsoft/PhonMatchNet.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}