{"id":"https://openalex.org/W2796868621","doi":"https://doi.org/10.1109/icassp.2018.8461580","title":"3-D CNN Models for Far-Field Multi-Channel Speech Recognition","display_name":"3-D CNN Models for Far-Field Multi-Channel Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2796868621","doi":"https://doi.org/10.1109/icassp.2018.8461580","mag":"2796868621"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Indian Institute of Science, Bangalore"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081105332","display_name":"Vijayaditya Peddinti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijayaditya Peddinti","raw_affiliation_strings":["Google, Inc, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google, Inc, U.S.A","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002536077"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":3.6484,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93990244,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5499","last_page":"5503"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.7620989680290222},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6706114411354065},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5172737240791321},{"id":"https://openalex.org/keywords/near-and-far-field","display_name":"Near and far field","score":0.46696168184280396},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45147812366485596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.352234423160553},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1469402313232422},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.058068811893463135},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05298662185668945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620989680290222},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6706114411354065},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5172737240791321},{"id":"https://openalex.org/C25227671","wikidata":"https://www.wikidata.org/wiki/Q13405516","display_name":"Near and far field","level":2,"score":0.46696168184280396},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45147812366485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.352234423160553},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1469402313232422},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.058068811893463135},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05298662185668945},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8461580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:60965","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1926954649","https://openalex.org/W1935589317","https://openalex.org/W1973669708","https://openalex.org/W1983364832","https://openalex.org/W1989314204","https://openalex.org/W2062227835","https://openalex.org/W2079623482","https://openalex.org/W2083751884","https://openalex.org/W2103088716","https://openalex.org/W2107992675","https://openalex.org/W2125336414","https://openalex.org/W2130361043","https://openalex.org/W2143612262","https://openalex.org/W2148613904","https://openalex.org/W2301358467","https://openalex.org/W2398972335","https://openalex.org/W2402146185","https://openalex.org/W2404568753","https://openalex.org/W2407080277","https://openalex.org/W2506203739","https://openalex.org/W2510616059","https://openalex.org/W2514741789","https://openalex.org/W2589857635","https://openalex.org/W2616139854","https://openalex.org/W2727634334","https://openalex.org/W2729190387","https://openalex.org/W2749980185","https://openalex.org/W2767071179","https://openalex.org/W2964084166","https://openalex.org/W4206633762","https://openalex.org/W6743356167"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2893763841","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2778699561","https://openalex.org/W2995996972","https://openalex.org/W2359317704","https://openalex.org/W2312116756","https://openalex.org/W3208187232","https://openalex.org/W3200991537"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,14],"recognition":[2,22],"(ASR)":[3],"in":[4,30],"far-field":[5,58],"reverberant":[6],"environments,":[7],"especially":[8],"when":[9],"involving":[10],"natural":[11],"conversational":[12],"multiparty":[13],"conditions,":[15],"is":[16],"challenging":[17],"even":[18],"with":[19,116],"the":[20,31,37,69,82,88,95,105,112,128],"state-of-the-art":[21],"methodologies.":[23],"The":[24,99],"two":[25],"main":[26],"issues":[27],"are":[28,79],"artifacts":[29],"signal":[32],"due":[33],"to":[34,72],"reverberation":[35],"and":[36,87],"presence":[38],"of":[39,68,111,124],"multiple":[40],"speakers.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"a":[47,117],"three":[48],"dimensional":[49],"(3-D)":[50],"convolutional":[51,76],"neural":[52],"network":[53],"(CNN)":[54],"architecture":[55,61],"for":[56],"multi-channel":[57,113],"ASR.":[59],"This":[60],"processes":[62],"time,":[63],"frequency":[64],"&":[65],"channel":[66],"dimensions":[67],"input":[70],"spectrogram":[71],"learn":[73],"representations":[74],"using":[75,94],"layers.":[77],"Experiments":[78],"performed":[80],"on":[81,132],"REVERB":[83],"challenge":[84],"LVCSR":[85,92],"task":[86,93],"augmented":[89],"multi-party":[90],"(AMI)":[91],"array":[96],"microphone":[97],"recordings.":[98],"proposed":[100],"method":[101],"shows":[102],"improvements":[103,123],"over":[104,127],"baseline":[106,130],"system":[107,131],"that":[108],"uses":[109],"beamforming":[110],"audio":[114],"along":[115],"2-D":[118],"conventional":[119],"CNN":[120],"framework":[121],"(absolute":[122],"1.1":[125],"%":[126],"beamformed":[129],"AMI":[133],"dataset).":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}