{"id":"https://openalex.org/W3198995983","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534109","title":"A domain-mismatch speech recognition system in radio communication based on improved spectrum augmentation","display_name":"A domain-mismatch speech recognition system in radio communication based on improved spectrum augmentation","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3198995983","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534109","mag":"3198995983"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5000710946","display_name":"Xiusong Sun","orcid":"https://orcid.org/0000-0003-0232-7069"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiusong Sun","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics University Nanjing, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics University Nanjing, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022836264","display_name":"Qun Yang","orcid":"https://orcid.org/0000-0001-6824-8473"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qun Yang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics University Nanjing, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics University Nanjing, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053403785","display_name":"Shaohan Liu","orcid":"https://orcid.org/0000-0001-6967-0262"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohan Liu","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics University Nanjing, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics University Nanjing, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000710946"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54961843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"521","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976000189781189,"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":0.9933000206947327,"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":0.8176140189170837},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7772706747055054},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6761224269866943},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5496651530265808},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5267733335494995},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5190771222114563},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4663870334625244},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4467754364013672},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4451425075531006},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43813151121139526},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4321005940437317},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.41025251150131226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36011144518852234},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.350044846534729},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.1880117952823639},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17956608533859253},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08997172117233276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176140189170837},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7772706747055054},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6761224269866943},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5496651530265808},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5267733335494995},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5190771222114563},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4663870334625244},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4467754364013672},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4451425075531006},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43813151121139526},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4321005940437317},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.41025251150131226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36011144518852234},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.350044846534729},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.1880117952823639},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17956608533859253},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08997172117233276},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2097464745","https://openalex.org/W2099621636","https://openalex.org/W2102113734","https://openalex.org/W2106822551","https://openalex.org/W2129450987","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2284628133","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2889048668","https://openalex.org/W2914018192","https://openalex.org/W2919115771","https://openalex.org/W2936547119","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6675409298","https://openalex.org/W6695553435","https://openalex.org/W6713762819","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W2401089611","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W4255044973","https://openalex.org/W2890936991","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W3160071434","https://openalex.org/W2727729836"],"abstract_inverted_index":{"Most":[0],"of":[1,14,32,68,98,121,124,151,158,173,177,189],"the":[2,11,15,29,33,57,66,69,74,99,114,141,175,178,183,187],"current":[3],"automatic":[4],"speech":[5,47,79,108,144],"recognition":[6,58,145],"systems":[7],"(ASR)":[8],"require":[9],"that":[10,92,111],"data":[12,30,80,101],"domain":[13],"test":[16],"set":[17,20],"and":[18,45,76,128,147,156,182],"training":[19],"are":[21,35],"similar":[22],"to":[23,85,91],"obtain":[24,86],"satisfactory":[25],"accuracy.":[26],"However,":[27],"when":[28],"style":[31],"two":[34],"different,":[36],"such":[37],"as":[38],"different":[39,42,46,100],"background":[40],"noise,":[41],"sampling":[43,180],"rates,":[44],"speeds,":[48],"etc.,":[49],"they":[50],"will":[51],"have":[52],"a":[53,171],"bad":[54],"influence":[55],"on":[56,131,140],"results.":[59],"In":[60],"some":[61,94],"areas":[62,96],"like":[63],"radio":[64,142],"communications,":[65],"performance":[67],"acoustics":[70],"models":[71],"trained":[72],"by":[73],"pure":[75],"noise-free":[77],"Mandarin":[78,143],"which":[81],"is":[82,87],"relatively":[83],"easy":[84],"still":[88],"not":[89],"comparable":[90],"in":[93],"other":[95,164],"because":[97],"styles.":[102],"Therefore,":[103],"we":[104,169],"investigate":[105],"an":[106],"audio-level":[107],"augmentation":[109,118,165],"method":[110,139,172],"directly":[112],"processes":[113],"raw":[115],"signal.":[116],"The":[117],"policy":[119],"consists":[120],"masking":[122],"blocks":[123],"frequency":[125],"channels":[126],"randomly":[127],"specifically":[129],"based":[130],"Discrete":[132],"Fourier":[133],"Transformation":[134],"(DFT).":[135],"We":[136],"apply":[137],"our":[138],"task":[146],"achieve":[148],"24%":[149],"improvement":[150],"Character":[152],"Error":[153,160],"Rate":[154,161],"(CER)":[155],"22%":[157],"Word":[159],"(WER)":[162],"over":[163],"policies":[166],"relatively.":[167],"Besides,":[168],"propose":[170],"eliminating":[174],"impact":[176],"original":[179],"rate":[181],"experimental":[184],"results":[185],"verify":[186],"effectiveness":[188],"it.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}