{"id":"https://openalex.org/W2785600113","doi":"https://doi.org/10.1109/taslp.2018.2795754","title":"FMLLR Speaker Normalization With i-Vector: In Pseudo-FMLLR and Distillation Framework","display_name":"FMLLR Speaker Normalization With i-Vector: In Pseudo-FMLLR and Distillation Framework","publication_year":2018,"publication_date":"2018-01-19","ids":{"openalex":"https://openalex.org/W2785600113","doi":"https://doi.org/10.1109/taslp.2018.2795754","mag":"2785600113"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2795754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2795754","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5074777875","display_name":"Neethu Mariam Joy","orcid":"https://orcid.org/0000-0003-2460-5189"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neethu Mariam Joy","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Madras, India"],"raw_orcid":"https://orcid.org/0000-0003-2460-5189","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022349534","display_name":"Sandeep Reddy Kothinti","orcid":"https://orcid.org/0000-0002-1574-3339"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandeep Reddy Kothinti","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Madras, India"],"raw_orcid":"https://orcid.org/0000-0002-1574-3339","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srinivasan Umesh","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Madras, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.9265,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81348218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"26","issue":"4","first_page":"797","last_page":"805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.7642052173614502},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7458930611610413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.742957353591919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6920126080513},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6373134255409241},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.576400637626648},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5034584403038025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47896602749824524},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4661114811897278},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45807337760925293},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42098289728164673},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4207513630390167},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.23896554112434387},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17770534753799438},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0894453227519989}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7642052173614502},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7458930611610413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742957353591919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6920126080513},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6373134255409241},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.576400637626648},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5034584403038025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47896602749824524},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4661114811897278},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45807337760925293},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42098289728164673},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4207513630390167},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.23896554112434387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17770534753799438},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0894453227519989},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2795754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2795754","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1537275613","https://openalex.org/W1821462560","https://openalex.org/W1973681148","https://openalex.org/W1985368711","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2010362084","https://openalex.org/W2044893557","https://openalex.org/W2067562626","https://openalex.org/W2078528584","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2090320273","https://openalex.org/W2157711090","https://openalex.org/W2160306971","https://openalex.org/W2173379916","https://openalex.org/W2253986341","https://openalex.org/W2295119550","https://openalex.org/W2404620314","https://openalex.org/W2408713104","https://openalex.org/W2512865187","https://openalex.org/W2515525878","https://openalex.org/W2624390389","https://openalex.org/W2750536063","https://openalex.org/W2962946266","https://openalex.org/W4293390340","https://openalex.org/W6631362777","https://openalex.org/W6632212032","https://openalex.org/W6638523607","https://openalex.org/W6685316698","https://openalex.org/W6697090674","https://openalex.org/W6713729801","https://openalex.org/W6714125293"],"related_works":["https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W2591697403","https://openalex.org/W4321441197","https://openalex.org/W2359348847","https://openalex.org/W4294432981","https://openalex.org/W2186375278"],"abstract_inverted_index":{"When":[0],"an":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"system":[6],"is":[7],"deployed":[8],"for":[9,21,120],"real-world":[10],"applications,":[11],"it":[12],"often":[13],"receives":[14],"only":[15],"one":[16],"utterance":[17,25],"at":[18,68,73],"a":[19,132,137,150],"time":[20],"decoding.":[22,126],"This":[23],"single":[24],"could":[26],"be":[27,56,118,171],"of":[28,41,76,82,96,108,149,188],"short":[29],"duration":[30],"depending":[31],"on":[32,141,154,183,202],"the":[33,80,94,145,159,162,166,177,193],"ASR":[34],"task.":[35],"In":[36,58,157],"these":[37],"cases,":[38],"robust":[39],"estimation":[40],"speaker":[42,65],"normalizing":[43],"methods":[44,195],"like":[45],"feature-space":[46],"maximum":[47],"likelihood":[48],"linear":[49],"regression":[50],"(FMLLR)":[51],"and":[52,71,84,110,125,147,185,208],"i-vectors":[53,85,175],"may":[54],"not":[55],"feasible.":[57],"this":[59],"paper,":[60],"we":[61,92,130],"propose":[62,93,131],"two":[63],"unsupervised":[64],"normalization":[66],"techniques-one":[67],"feature":[69,90],"level":[70,75],"other":[72],"model":[74,123,128],"acoustic":[77,122],"modeling-to":[78],"overcome":[79],"drawbacks":[81],"FMLLR":[83,111,142,168],"in":[86,164,214],"real-time":[87,215],"scenarios.":[88],"At":[89,127],"level,":[91,129],"use":[95],"deep":[97],"neural":[98],"networks":[99],"(DNN)":[100],"to":[101,176],"generate":[102],"pseudo-FMLLR":[103,114],"features":[104,115,143],"from":[105],"time-synchronous":[106],"pair":[107],"filterbank":[109,155,179,207,212],"features.":[112,156,180],"These":[113],"can":[116,170],"then":[117],"used":[119],"DNN":[121,139,152],"training":[124,146],"generalized":[133],"distillation":[134],"framework,":[135],"where":[136],"teacher":[138],"trained":[140,153,201],"guides":[144],"optimization":[148],"student":[151],"both":[158],"proposed":[160,194],"methods,":[161],"ambiguity":[163],"choosing":[165],"speaker-specific":[167],"transform":[169],"reduced":[172],"by":[173],"augmenting":[174],"input":[178],"Experiments":[181],"conducted":[182],"33-h":[184],"110-h":[186],"subsets":[187],"Switchboard":[189],"corpus":[190],"show":[191],"that":[192],"provide":[196],"significant":[197],"gains":[198],"over":[199],"DNNs":[200],"FMLLR,":[203,206],"i-vector":[204],"appended":[205,211],"i":[209],"-vector":[210],"features,":[213],"scenario.":[216]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}