{"id":"https://openalex.org/W1985371235","doi":"https://doi.org/10.1109/icassp.2014.6853591","title":"Improving DNN speaker independence with I-vector inputs","display_name":"Improving DNN speaker independence with I-vector inputs","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1985371235","doi":"https://doi.org/10.1109/icassp.2014.6853591","mag":"1985371235"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Senior","raw_affiliation_strings":["Google Inc., New York","Google Inc., New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050898122","display_name":"Ignacio L\u00f3pez Moreno","orcid":"https://orcid.org/0000-0002-0900-3473"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ignacio Lopez-Moreno","raw_affiliation_strings":["Google Inc., New York","Google Inc., New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079708487"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":39.2652,"has_fulltext":false,"cited_by_count":195,"citation_normalized_percentile":{"value":0.99817375,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"229"},"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":0.9998000264167786,"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":0.9987999796867371,"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":0.7665109634399414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7185178399085999},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6966149806976318},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6322182416915894},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5974457263946533},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5569872260093689},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5444461107254028},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4963379502296448},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4897489547729492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.461364209651947},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44675326347351074},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43136757612228394},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36178964376449585},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3312612771987915},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10637089610099792},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0656137764453888}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7665109634399414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7185178399085999},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6966149806976318},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6322182416915894},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5974457263946533},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5569872260093689},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5444461107254028},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4963379502296448},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4897489547729492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.461364209651947},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44675326347351074},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43136757612228394},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36178964376449585},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3312612771987915},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10637089610099792},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0656137764453888},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W1506806321","https://openalex.org/W1537275613","https://openalex.org/W1901264808","https://openalex.org/W1979058968","https://openalex.org/W1993409002","https://openalex.org/W2000629566","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2033256038","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2150769028","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2165108269","https://openalex.org/W2184045248","https://openalex.org/W2296516251","https://openalex.org/W2296748324","https://openalex.org/W2403731734","https://openalex.org/W2406312423","https://openalex.org/W6697811694","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W4255044973","https://openalex.org/W2890936991","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2464377622","https://openalex.org/W2394963835"],"abstract_inverted_index":{"We":[0,57],"propose":[1],"providing":[2],"additional":[3],"utterance-level":[4],"features":[5],"as":[6],"inputs":[7],"to":[8,14,42],"a":[9,52,64],"deep":[10],"neural":[11],"network":[12],"(DNN)":[13],"facilitate":[15],"speaker,":[16],"channel":[17],"and":[18],"background":[19],"normalization.":[20],"Modifications":[21],"of":[22,60],"the":[23,61],"basic":[24],"algorithm":[25,62],"are":[26,40],"developed":[27],"which":[28],"result":[29],"in":[30,33,51],"significant":[31],"reductions":[32],"word":[34],"error":[35],"rates":[36],"(WERs).":[37],"The":[38],"algorithms":[39],"shown":[41],"combine":[43],"well":[44],"with":[45],"speaker":[46],"adaptation":[47],"by":[48],"backpropagation,":[49],"resulting":[50],"9%":[53],"relative":[54],"WER":[55],"reduction.":[56],"address":[58],"implementation":[59],"for":[63],"streaming":[65],"task.":[66]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":36},{"year":2015,"cited_by_count":28},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}