{"id":"https://openalex.org/W7100893446","doi":null,"title":"MULTITASK LEARNING IN CONNECTIONIST SPEECH RECOGNITION","display_name":"MULTITASK LEARNING IN CONNECTIONIST SPEECH RECOGNITION","publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7100893446"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.107.4108","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.107.4108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.assta.org/sst/2004/proceedings/papers/sst2004-64.pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7100893446"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Youyi Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youyi Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fei Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Siddharth Sehgal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddharth Sehgal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Swati Gupta","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swati Gupta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jingsheng Du","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingsheng Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chee Hong Tham","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chee Hong Tham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Phil Green","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phil Green","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031222393","display_name":"Vincent Wan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0012000000569969416,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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/multi-task-learning","display_name":"multi-task learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8259999752044678},{"id":"https://openalex.org/keywords/speech-recognition-in-noise","display_name":"speech recognition in noise","score":0.7910000085830688},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.9879999756813049},{"id":"https://openalex.org/keywords/gender-classification","display_name":"gender classification","score":0.9480000138282776},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.9430000185966492},{"id":"https://openalex.org/keywords/task-interaction","display_name":"task interaction","score":0.4259999990463257},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.4909999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350000143051147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6736000180244446},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6335999965667725},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6266999840736389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46880000829696655},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4075999855995178},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C202101335","wikidata":"https://www.wikidata.org/wiki/Q7002166","display_name":"Neurocomputational speech processing","level":4,"score":0.34220001101493835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.2870999872684479},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.107.4108","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.107.4108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.assta.org/sst/2004/proceedings/papers/sst2004-64.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.136.6680","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.6680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.shef.ac.uk/~vinny/docs/pdf/asr.sst2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387789961","https://openalex.org/W173856587","https://openalex.org/W2346842942","https://openalex.org/W2572178803","https://openalex.org/W2586410710","https://openalex.org/W2396990910","https://openalex.org/W4385823217","https://openalex.org/W4297841672","https://openalex.org/W2566925314","https://openalex.org/W2565624985"],"abstract_inverted_index":{"Humans":[0],"do":[1],"not":[2],"learn":[3],"new":[4],"tasks":[5,30,74],"in":[6,47],"isolation:":[7],"for":[8],"instance":[9],"speech":[10,50],"recognition":[11,54],"interacts":[12],"with":[13],"speaker":[14],"recognition.":[15],"Multitask":[16],"Learning":[17],"(MTL)":[18],"attempts":[19],"to":[20,31,43,65,80],"take":[21],"advantage":[22],"of":[23,41],"these":[24],"interactions":[25],"by":[26],"adding":[27],"additional,":[28],"related":[29,72],"the":[32,83],"main":[33,84],"task.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"present":[39],"applications":[40],"MTL":[42],"Automatic":[44],"Speech":[45],"Recognition":[46],"noise,":[48],"incorporating":[49],"enhancement":[51],"and":[52],"gender":[53],"as":[55],"additional":[56],"tasks.":[57,68],"A":[58],"Recurrent":[59],"Neural":[60],"Net":[61],"architecture":[62],"is":[63],"used":[64],"integrate":[66],"multiple":[67],"Results":[69],"show":[70],"that":[71],"extra":[73],"can":[75],"indeed":[76],"produce":[77],"significant":[78],"improvements":[79],"performance":[81],"on":[82],"task,":[85],"i.e.":[86],"ASR.":[87],"1.":[88]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2025-10-27T00:00:00"}