{"id":"https://openalex.org/W3198259309","doi":"https://doi.org/10.21437/interspeech.2021-356","title":"Improving Time Delay Neural Network Based Speaker Recognition with Convolutional Block and Feature Aggregation Methods","display_name":"Improving Time Delay Neural Network Based Speaker Recognition with Convolutional Block and Feature Aggregation Methods","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198259309","doi":"https://doi.org/10.21437/interspeech.2021-356","mag":"3198259309"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-356","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5100430743","display_name":"Yujia Zhang","orcid":"https://orcid.org/0000-0003-3991-7388"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu-Jia Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012592197","display_name":"Yih-Wen Wang","orcid":"https://orcid.org/0000-0003-1805-3234"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yih-Wen Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087434278","display_name":"Chia-Ping Chen","orcid":"https://orcid.org/0000-0002-7022-3061"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chia-Ping Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107138318","display_name":"Chung-Li Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung-Li Lu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016449606","display_name":"Bo-Cheng Chan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo-Cheng Chan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100430743"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6798,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75818527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9943000078201294,"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":0.8081554770469666},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7006636261940002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6520615816116333},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6305885314941406},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6175962090492249},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5830633044242859},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5537989139556885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4827674925327301},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4620676636695862},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4590455889701843},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43531933426856995},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06683284044265747}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081554770469666},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7006636261940002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6520615816116333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6305885314941406},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6175962090492249},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5830633044242859},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5537989139556885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4827674925327301},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4620676636695862},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4590455889701843},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43531933426856995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06683284044265747},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-356","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/W2121812409","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2696967604","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2922509574","https://openalex.org/W2928165649","https://openalex.org/W2969985801","https://openalex.org/W3020953549","https://openalex.org/W3034752215","https://openalex.org/W3122060391"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W2811106690","https://openalex.org/W4239306820","https://openalex.org/W1560125148","https://openalex.org/W3081952170","https://openalex.org/W4385719553","https://openalex.org/W2349696592","https://openalex.org/W1985270221"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
