{"id":"https://openalex.org/W4405709533","doi":"https://doi.org/10.1109/iscslp63861.2024.10800523","title":"Query-by-Example Speech Search using Mamba and Random Offset Mixed Padding","display_name":"Query-by-Example Speech Search using Mamba and Random Offset Mixed Padding","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709533","doi":"https://doi.org/10.1109/iscslp63861.2024.10800523"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5113173970","display_name":"Kaixin Yang","orcid":"https://orcid.org/0009-0008-5234-2316"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaixin Yang","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046466203","display_name":"Gaofeng Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaofeng Cheng","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052454197","display_name":"Li Ta","orcid":"https://orcid.org/0000-0001-5431-9787"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ta Li","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651591","display_name":"Qingwei Zhao","orcid":"https://orcid.org/0000-0001-9272-2614"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingwei Zhao","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences,Key Laboratory of Speech Acoustics and Content Understanding","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113173970"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2196048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"726","last_page":"730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9815999865531921,"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":0.9815999865531921,"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":0.9610999822616577,"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":0.9437999725341797,"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/padding","display_name":"Padding","score":0.8165905475616455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7432982921600342},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6490646004676819},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3974100351333618},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1680058240890503},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08653217554092407}],"concepts":[{"id":"https://openalex.org/C165435473","wikidata":"https://www.wikidata.org/wiki/Q1509884","display_name":"Padding","level":2,"score":0.8165905475616455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432982921600342},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6490646004676819},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3974100351333618},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1680058240890503},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08653217554092407}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1496120315","https://openalex.org/W2059652594","https://openalex.org/W2064675550","https://openalex.org/W2114347655","https://openalex.org/W2190506272","https://openalex.org/W2194775991","https://openalex.org/W2747874407","https://openalex.org/W2889270419","https://openalex.org/W2944964836","https://openalex.org/W2962736743","https://openalex.org/W2962980711","https://openalex.org/W2963775347","https://openalex.org/W2963879199","https://openalex.org/W2963879374","https://openalex.org/W3029661253","https://openalex.org/W3198035615","https://openalex.org/W4283694719","https://openalex.org/W4293363567","https://openalex.org/W4318464643","https://openalex.org/W4379797396","https://openalex.org/W4390872521","https://openalex.org/W6771467084","https://openalex.org/W6780226713","https://openalex.org/W6795140394","https://openalex.org/W6859298233"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2142641794","https://openalex.org/W4384947563","https://openalex.org/W2946726629","https://openalex.org/W4231428344","https://openalex.org/W4391601668","https://openalex.org/W4322753435","https://openalex.org/W4243974052"],"abstract_inverted_index":{"State-of-the-art":[0],"approaches":[1],"to":[2,47],"Query-by-Example":[3],"speech":[4,16],"search":[5],"are":[6],"usually":[7],"based":[8,33],"on":[9,34],"acoustic":[10],"word":[11],"embedding":[12],"(AWE),":[13],"representing":[14],"variable-length":[15],"segments":[17],"with":[18,82,93,102],"fixed-dimensional":[19],"vectors":[20],"using":[21],"metric":[22],"learning.":[23],"In":[24,45],"this":[25],"paper,":[26],"we":[27,63],"propose":[28,65],"a":[29,36,66],"novel":[30,67],"AWE":[31],"network":[32,91],"Mamba,":[35],"new":[37],"state":[38],"space":[39],"model":[40],"architecture":[41],"for":[42],"information-dense":[43],"data.":[44],"order":[46],"further":[48],"mitigate":[49],"the":[50,53,57,74,83,99,110,116],"mismatch":[51],"between":[52],"training":[54,75],"phase":[55,59],"and":[56],"testing":[58],"of":[60,118],"AWE-based":[61,119],"models,":[62],"also":[64,107],"audio":[68],"segment":[69],"padding":[70,112],"method":[71,113],"used":[72],"in":[73],"phase,":[76],"Random":[77,94],"Offset":[78,95],"Mixed":[79,96],"Padding.":[80],"Comparisons":[81],"state-of-the-art":[84],"methods":[85],"show":[86],"that":[87,109],"our":[88],"method,":[89],"Mamba-based":[90],"together":[92],"Padding,":[97],"achieves":[98],"best":[100],"performance":[101,117],"significantly":[103],"fewer":[104],"parameters.":[105],"We":[106],"demonstrate":[108],"proposed":[111],"can":[114],"enhance":[115],"baseline":[120],"models.":[121]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}