{"id":"https://openalex.org/W4319862692","doi":"https://doi.org/10.1109/slt54892.2023.10022757","title":"SIMD-Size Aware Weight Regularization for Fast Neural Vocoding on CPU","display_name":"SIMD-Size Aware Weight Regularization for Fast Neural Vocoding on CPU","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862692","doi":"https://doi.org/10.1109/slt54892.2023.10022757"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022757","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022757","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5076754533","display_name":"Hiroki Kanagawa","orcid":null},"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":true,"raw_author_name":"Hiroki Kanagawa","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"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":"Yusuke Ijima","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076754533"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.1107,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.2131063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"955","last_page":"961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9986000061035156,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.790062427520752},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7749172449111938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7225551605224609},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5497286319732666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4584393799304962},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3447505831718445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2532695233821869}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.790062427520752},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7749172449111938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225551605224609},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5497286319732666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4584393799304962},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3447505831718445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2532695233821869},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022757","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022757","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2460144244","https://openalex.org/W2519091744","https://openalex.org/W2764043458","https://openalex.org/W2769810959","https://openalex.org/W2785516183","https://openalex.org/W2896457183","https://openalex.org/W2898847420","https://openalex.org/W2962965870","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963975282","https://openalex.org/W2964041258","https://openalex.org/W2968917279","https://openalex.org/W3015338123","https://openalex.org/W3015347659","https://openalex.org/W3015878662","https://openalex.org/W3016342592","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3095851005","https://openalex.org/W3097538987","https://openalex.org/W4224925626","https://openalex.org/W4285284469","https://openalex.org/W4294619240","https://openalex.org/W4297841285","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6687032555","https://openalex.org/W6726275242","https://openalex.org/W6739901393","https://openalex.org/W6745148473","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6755207826","https://openalex.org/W6767164110","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6809913336"],"related_works":["https://openalex.org/W2291920536","https://openalex.org/W2022397046","https://openalex.org/W2162726111","https://openalex.org/W1603583590","https://openalex.org/W338671845","https://openalex.org/W2063770303","https://openalex.org/W2018511057","https://openalex.org/W2286348849","https://openalex.org/W1587248296","https://openalex.org/W2001175489"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"weight":[3,48,75],"regularization":[4,97,124],"for":[5,56],"a":[6,15,20,24,74,78],"faster":[7,137],"neural":[8],"vocoder.":[9],"Pruning":[10],"time-consuming":[11],"DNN":[12],"modules":[13],"is":[14,33],"promising":[16],"way":[17],"to":[18,129],"realize":[19],"real-time":[21],"vocoder":[22,121],"on":[23,100],"CPU":[25],"(e.g.":[26],"WaveRNN,":[27],"LPCNet).":[28],"Regularization":[29],"that":[30,81,106,130],"encourages":[31],"sparsity":[32],"also":[34],"effective":[35],"in":[36,53,89,108],"avoiding":[37],"the":[38,45,82,94,116],"quality":[39],"degradation":[40],"created":[41],"by":[42,86],"pruning.":[43],"However,":[44],"orders":[46],"of":[47],"matrices":[49],"must":[50],"be":[51],"contiguous":[52],"SIMD":[54,66],"size":[55,67,88],"fast":[57],"vocoding.":[58],"To":[59],"ensure":[60],"this":[61],"order,":[62],"we":[63],"propose":[64],"explicit":[65],"aware":[68],"regularization.":[69,143],"Our":[70],"proposed":[71,123],"method":[72],"reshapes":[73],"matrix":[76],"into":[77],"tensor":[79],"so":[80],"weights":[83],"are":[84],"aligned":[85],"group":[87,95,113],"advance,":[90],"and":[91,111,133],"then":[92],"computes":[93],"Lasso-like":[96],"loss.":[98],"Experiments":[99],"70%":[101],"sparse":[102],"subband":[103],"WaveRNN":[104],"show":[105],"pruning":[107,132],"conventional":[109,140],"Lasso":[110,114],"column-wise":[112],"degrades":[115],"synthetic":[117],"speech's":[118],"naturalness.":[119],"The":[120],"with":[122],"1)":[125],"achieves":[126],"comparable":[127],"naturalness":[128],"without":[131],"2)":[134],"performs":[135],"meaningfully":[136],"than":[138],"other":[139],"vocoders":[141],"using":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}