{"id":"https://openalex.org/W3015465870","doi":"https://doi.org/10.1109/icassp40776.2020.9052966","title":"Mspec-Net : Multi-Domain Speech Conversion Network","display_name":"Mspec-Net : Multi-Domain Speech Conversion Network","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015465870","doi":"https://doi.org/10.1109/icassp40776.2020.9052966","mag":"3015465870"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5037317140","display_name":"Harshit Malaviya","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harshit Malaviya","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109455358","display_name":"Jui Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jui Shah","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018555559","display_name":"Maitreya Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Maitreya Patel","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046427146","display_name":"Jalansh Munshi","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jalansh Munshi","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.805,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.75572235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7764","last_page":"7768"},"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":0.9998000264167786,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8165562748908997},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6773412227630615},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6234229803085327},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6096022129058838},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5767573118209839},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5365822911262512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3782617151737213},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34165412187576294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08895987272262573},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07841280102729797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165562748908997},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6773412227630615},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6234229803085327},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6096022129058838},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5767573118209839},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5365822911262512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3782617151737213},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34165412187576294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08895987272262573},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07841280102729797},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1540787848","https://openalex.org/W1550001449","https://openalex.org/W2022045190","https://openalex.org/W2042204480","https://openalex.org/W2056852181","https://openalex.org/W2071431631","https://openalex.org/W2095026407","https://openalex.org/W2105677113","https://openalex.org/W2119648481","https://openalex.org/W2120605154","https://openalex.org/W2128532956","https://openalex.org/W2295406225","https://openalex.org/W2400434184","https://openalex.org/W2550821151","https://openalex.org/W2888796252","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2963695770","https://openalex.org/W2964121744","https://openalex.org/W2972986317","https://openalex.org/W2987496713","https://openalex.org/W3012437242","https://openalex.org/W3137116880","https://openalex.org/W4206495986","https://openalex.org/W6631190155","https://openalex.org/W6632127171","https://openalex.org/W6697307144","https://openalex.org/W6712874156","https://openalex.org/W6762533536"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2357191878","https://openalex.org/W2181948922","https://openalex.org/W1997078944","https://openalex.org/W107154053","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2151415191","https://openalex.org/W2151664070","https://openalex.org/W2346347014"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,12,49,77,122,134],"multi-domain":[6],"speech":[7,42],"conversion":[8,47,82,99,153],"technique":[9],"by":[10,32,37,85],"proposing":[11],"Multi-domain":[13],"Speech":[14],"Conversion":[15],"Network":[16],"(MSpeC-Net)":[17],"architecture":[18],"for":[19,54,151],"solving":[20],"the":[21,33,38,56,80,87,101,107,147],"less-explored":[22],"area":[23],"of":[24,58,126],"Non-Audible":[25],"Murmur-to-SPeeCH":[26],"(NAM2-SPCH)":[27],"conversion.":[28],"The":[29,66],"murmur":[30],"produced":[31],"speaker":[34],"and":[35,51,90,106,118,128,137],"captured":[36],"NAM":[39,59],"microphone":[40],"undergoes":[41],"quality":[43],"degradation.":[44],"Hence,":[45],"NAM2SPCH":[46,98,140,152],"becomes":[48],"necessary":[50],"challenging":[52],"task":[53],"improving":[55],"intelligibility":[57],"signal.":[60],"MSpeC-Net":[61,145],"contains":[62],"three":[63],"domain-specific":[64],"autoencoders.":[65],"multiple":[67],"encoder-decoders":[68],"are":[69],"aligned":[70],"using":[71,86,100,115],"latent":[72],"consistency":[73],"loss":[74],"in":[75,133],"such":[76],"way":[78],"that":[79],"desired":[81],"is":[83],"achieved":[84],"source":[88,104],"encoder":[89,105],"target":[91,108],"decoder":[92],"only.":[93],"We":[94,110],"have":[95],"performed":[96],"zero-pair":[97],"interaction":[102],"between":[103],"decoder.":[109],"evaluated":[111],"our":[112],"proposed":[113],"method":[114],"both":[116],"objective":[117],"subjective":[119],"evaluations.":[120],"With":[121],"Mean":[123],"Opinion":[124],"Score":[125],"3.26":[127],"3.12":[129],"on":[130],"an":[131,138],"average":[132],"direct":[135],"NAM2SPCH,":[136],"indirect":[139],"(i.e.,":[141],"NAM-to-whisper-to-speech)":[142],"conversion,":[143],"respectively.":[144],"achieves":[146],"perceptually":[148],"significant":[149],"improvement":[150],"system.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}