{"id":"https://openalex.org/W2982471419","doi":"https://doi.org/10.1109/msp.2019.2918706","title":"Speech Processing for Digital Home Assistants: Combining Signal Processing With Deep-Learning Techniques","display_name":"Speech Processing for Digital Home Assistants: Combining Signal Processing With Deep-Learning Techniques","publication_year":2019,"publication_date":"2019-10-30","ids":{"openalex":"https://openalex.org/W2982471419","doi":"https://doi.org/10.1109/msp.2019.2918706","mag":"2982471419"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2019.2918706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2019.2918706","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"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 Signal Processing Magazine","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/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]},{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Communications Engineering, University of Paderborn, Paderborn, Germany","Rheinisch-Westf\u00e4lische Technische Hochschule Aachen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9468-7330","affiliations":[{"raw_affiliation_string":"Communications Engineering, University of Paderborn, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]},{"raw_affiliation_string":"Rheinisch-Westf\u00e4lische Technische Hochschule Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["Nippon Telegraph and Telephone Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7487-7150","affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google Tokyo, Tokyo, Japan","Technical University of Eindhoven, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-4527-0197","affiliations":[{"raw_affiliation_string":"Google Tokyo, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"Technical University of Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012163532","display_name":"Bj\u00f6rn Hoffmeister","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]},{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Bjorn Hoffmeister","raw_affiliation_strings":["RWTH Aachen University, Germany","Siri Team, Apple Inc., Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Siri Team, Apple Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Applied Machine Learning, Facebook, Menlo Park, CA, USA","Carnegie Mellon University, Pittsburgh, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Machine Learning, Facebook, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, Pennsylvania","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041575981","display_name":"Mehrez Souden","orcid":null},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Mehrez Souden","raw_affiliation_strings":["Institut National de la Recherche Scientifique, University of Qu\u00e9bec, Montr\u00e9al, Canada","Interactive Media Group, Apple Inc., Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut National de la Recherche Scientifique, University of Qu\u00e9bec, Montr\u00e9al, Canada","institution_ids":["https://openalex.org/I159129438","https://openalex.org/I39481719"]},{"raw_affiliation_string":"Interactive Media Group, Apple Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5082075598"],"corresponding_institution_ids":["https://openalex.org/I206945453","https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":15.1893,"has_fulltext":false,"cited_by_count":152,"citation_normalized_percentile":{"value":0.99488584,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"36","issue":"6","first_page":"111","last_page":"124"},"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":0.9995999932289124,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7965282797813416},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6984933614730835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6727185249328613},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6411426663398743},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.578349769115448},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5261416435241699},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5119005441665649},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5004837512969971},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.46225684881210327},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4620022475719452},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.4560711979866028},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44744402170181274},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.44599488377571106},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4189285933971405},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41622045636177063},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.41077175736427307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.2962843179702759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.288621187210083},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.21157142519950867},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.16278955340385437},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1540490984916687},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12833333015441895},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08325797319412231}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965282797813416},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6984933614730835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6727185249328613},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6411426663398743},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.578349769115448},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5261416435241699},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5119005441665649},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5004837512969971},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.46225684881210327},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4620022475719452},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.4560711979866028},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44744402170181274},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.44599488377571106},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4189285933971405},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41622045636177063},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.41077175736427307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2962843179702759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.288621187210083},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.21157142519950867},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.16278955340385437},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1540490984916687},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12833333015441895},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08325797319412231},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msp.2019.2918706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2019.2918706","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"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 Signal Processing Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W76597279","https://openalex.org/W1553469512","https://openalex.org/W1973669708","https://openalex.org/W1983812858","https://openalex.org/W1987906574","https://openalex.org/W1996304098","https://openalex.org/W1997109056","https://openalex.org/W2034940213","https://openalex.org/W2043216213","https://openalex.org/W2046056978","https://openalex.org/W2065804682","https://openalex.org/W2117090122","https://openalex.org/W2117678320","https://openalex.org/W2130361043","https://openalex.org/W2139081859","https://openalex.org/W2140571699","https://openalex.org/W2143027228","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2242685705","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2402316076","https://openalex.org/W2403440562","https://openalex.org/W2407023693","https://openalex.org/W2460742184","https://openalex.org/W2513836842","https://openalex.org/W2517616541","https://openalex.org/W2519091744","https://openalex.org/W2559260703","https://openalex.org/W2563666542","https://openalex.org/W2568308529","https://openalex.org/W2584329820","https://openalex.org/W2589857635","https://openalex.org/W2591810467","https://openalex.org/W2600628583","https://openalex.org/W2617258110","https://openalex.org/W2622203030","https://openalex.org/W2625979394","https://openalex.org/W2640112133","https://openalex.org/W2747238065","https://openalex.org/W2747681982","https://openalex.org/W2748661748","https://openalex.org/W2769810959","https://openalex.org/W2787752687","https://openalex.org/W2797759721","https://openalex.org/W2803583024","https://openalex.org/W2810084418","https://openalex.org/W2884797218","https://openalex.org/W2887080793","https://openalex.org/W2889224938","https://openalex.org/W2890489755","https://openalex.org/W2890964092","https://openalex.org/W2891367150","https://openalex.org/W2891997645","https://openalex.org/W2949382160","https://openalex.org/W2949650786","https://openalex.org/W2954695182","https://openalex.org/W2962824709","https://openalex.org/W2963782041","https://openalex.org/W2964238697","https://openalex.org/W4294619240","https://openalex.org/W6603233860","https://openalex.org/W6680912004","https://openalex.org/W6687483927","https://openalex.org/W6712807204","https://openalex.org/W6713395095","https://openalex.org/W6714171909","https://openalex.org/W6726313835","https://openalex.org/W6735168207","https://openalex.org/W6738243166","https://openalex.org/W6738686518","https://openalex.org/W6739579368","https://openalex.org/W6743234192","https://openalex.org/W6743248688","https://openalex.org/W6743287238","https://openalex.org/W6746892368","https://openalex.org/W6748315512"],"related_works":["https://openalex.org/W2184127972","https://openalex.org/W3159882232","https://openalex.org/W2131711534","https://openalex.org/W2343205865","https://openalex.org/W2110852049","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2550171623","https://openalex.org/W2071795835","https://openalex.org/W2218471654"],"abstract_inverted_index":{"Once":[0],"a":[1,16,22,52,85,164],"popular":[2],"theme":[3],"of":[4,71,78,150,156],"futuristic":[5],"science":[6],"fiction":[7],"or":[8],"far-fetched":[9],"technology":[10],"forecasts,":[11],"digital":[12,106],"home":[13,107],"assistants":[14],"with":[15,105],"spoken":[17,50],"language":[18],"interface":[19],"have":[20],"become":[21],"ubiquitous":[23],"commodity":[24],"today.":[25],"This":[26],"success":[27],"has":[28,162],"been":[29],"made":[30],"possible":[31],"by":[32],"major":[33],"advancements":[34],"in":[35,84],"signal":[36,124],"processing":[37,96,119],"and":[38,64,120,129,132,144],"machine":[39],"learning":[40,160],"for":[41,123,142],"so-called":[42],"far-field":[43],"speech":[44,73,95,103,134,143],"recognition,":[45],"where":[46],"the":[47,55,91,93],"commands":[48],"are":[49,61],"at":[51],"distance":[53],"from":[54,66,147],"sound-capturing":[56],"device.":[57],"The":[58,76],"challenges":[59],"encountered":[60],"quite":[62],"unique":[63],"different":[65],"many":[67],"other":[68],"use":[69],"cases":[70],"automatic":[72],"recognition":[74],"(ASR).":[75],"purpose":[77],"this":[79],"article":[80],"is":[81,88],"to":[82,90],"describe,":[83],"way":[86],"that":[87,98],"amenable":[89],"nonspecialist,":[92],"key":[94],"algorithms":[97],"enable":[99],"reliable,":[100],"fully":[101],"hands-free":[102],"interaction":[104],"assistants.":[108],"These":[109],"technologies":[110],"include":[111],"multichannel":[112],"acoustic":[113],"echo":[114],"cancellation":[115],"(MAEC),":[116],"microphone":[117],"array":[118],"dereverberation":[121],"techniques":[122],"enhancement,":[125],"reliable":[126],"wake-up":[127],"word":[128],"end-of-interaction":[130],"detection,":[131],"high-quality":[133],"synthesis":[135],"as":[136,138],"well":[137],"sophisticated":[139],"statistical":[140],"models":[141],"language,":[145],"learned":[146],"large":[148],"amounts":[149],"heterogeneous":[151],"training":[152],"data.":[153],"In":[154],"all":[155],"these":[157],"fields,":[158],"deep":[159],"(DL)":[161],"played":[163],"critical":[165],"role.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}