{"id":"https://openalex.org/W3206531472","doi":"https://doi.org/10.1109/icassp43922.2022.9746314","title":"Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition","display_name":"Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206531472","doi":"https://doi.org/10.1109/icassp43922.2022.9746314","mag":"3206531472"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746314","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5074544822","display_name":"Yu\u2010Chen Hu","orcid":"https://orcid.org/0000-0002-5055-3645"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001511287","display_name":"Nana Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nana Hou","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418370","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0001-7587-3314"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6292","last_page":"6296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/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/end-to-end-principle","display_name":"End-to-end principle","score":0.8279925584793091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7146671414375305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7053077220916748},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4898242652416229},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4519970417022705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3731768727302551},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32569605112075806},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05908077955245972}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8279925584793091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146671414375305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7053077220916748},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4898242652416229},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4519970417022705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3731768727302551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32569605112075806},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05908077955245972},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746314","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W1956021273","https://openalex.org/W1989034586","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2071638348","https://openalex.org/W2141411743","https://openalex.org/W2156387975","https://openalex.org/W2250499536","https://openalex.org/W2963250244","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2972320711","https://openalex.org/W2972436155","https://openalex.org/W2998616931","https://openalex.org/W3011500442","https://openalex.org/W3028019732","https://openalex.org/W3095078764","https://openalex.org/W3096324175","https://openalex.org/W3097777922","https://openalex.org/W3109196171","https://openalex.org/W3113290170","https://openalex.org/W3142252347","https://openalex.org/W3163418064","https://openalex.org/W3173811143","https://openalex.org/W3186546663","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6682889407","https://openalex.org/W6691605950","https://openalex.org/W6739901393","https://openalex.org/W6787607767","https://openalex.org/W6799474351"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W3008587939","https://openalex.org/W4400488565","https://openalex.org/W4296070390"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"(SE)":[2],"aims":[3],"to":[4,13,41,62],"suppress":[5],"the":[6,15,22,26,31,42,67,78,91,103,112],"additive":[7],"noise":[8],"from":[9,66],"noisy":[10,72],"speech":[11,28,36,60],"signals":[12],"improve":[14],"speech\u2019s":[16],"perceptual":[17],"quality":[18],"and":[19,70],"intelligibility.":[20],"However,":[21],"over-suppression":[23],"phenomenon":[24],"in":[25,111],"enhanced":[27,68,114],"might":[29],"degrade":[30],"performance":[32],"of":[33,88],"downstream":[34],"automatic":[35],"recognition":[37,61],"(ASR)":[38],"task":[39],"due":[40],"missing":[43,109],"latent":[44],"information.":[45],"To":[46],"alleviate":[47],"such":[48],"problem,":[49],"we":[50],"propose":[51],"an":[52],"interactive":[53],"feature":[54,69],"fusion":[55],"network":[56],"(IFF-Net)":[57],"for":[58],"noise-robust":[59],"learn":[63],"complementary":[64],"information":[65,110],"original":[71],"feature.":[73,115],"Experimental":[74],"results":[75],"show":[76],"that":[77,102],"proposed":[79,104],"method":[80],"achieves":[81],"absolute":[82],"word":[83],"error":[84],"rate":[85],"(WER)":[86],"reduction":[87],"4.1%":[89],"over":[90],"best":[92],"baseline":[93],"on":[94],"RATS":[95],"Channel-A":[96],"corpus.":[97],"Our":[98],"further":[99],"analysis":[100],"indicates":[101],"IFF-Net":[105],"can":[106],"complement":[107],"some":[108],"over-suppressed":[113]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":18}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}