{"id":"https://openalex.org/W4406414478","doi":"https://doi.org/10.1109/lsp.2025.3528858","title":"SegINR: Segment-Wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech","display_name":"SegINR: Segment-Wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406414478","doi":"https://doi.org/10.1109/lsp.2025.3528858"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3528858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3528858","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Letters","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/A5027616639","display_name":"Minchan Kim","orcid":"https://orcid.org/0000-0002-8150-765X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minchan Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8150-765X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103069095","display_name":"Myeonghun Jeong","orcid":"https://orcid.org/0000-0002-4689-3110"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeonghun Jeong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4689-3110","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042018167","display_name":"Joun Yeop Lee","orcid":"https://orcid.org/0000-0002-3316-4808"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joun Yeop Lee","raw_affiliation_strings":["Samsung Research, Seoul, South Korea","Samsung Research, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-3316-4808","affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0568-4902","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00315027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"646","last_page":"650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/T10028","display_name":"Topic Modeling","score":0.9793999791145325,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9635999798774719,"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/sequence","display_name":"Sequence (biology)","score":0.6582151651382446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6551098227500916},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5634117126464844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5615956783294678},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5459782481193542},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5450385808944702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5362258553504944},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4011043906211853}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6582151651382446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6551098227500916},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5634117126464844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5615956783294678},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5459782481193542},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5450385808944702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5362258553504944},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4011043906211853},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3528858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3528858","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2105482032","https://openalex.org/W2747874407","https://openalex.org/W2903739847","https://openalex.org/W2962849139","https://openalex.org/W2963627347","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W3097777922","https://openalex.org/W3185635705","https://openalex.org/W3196001064","https://openalex.org/W4200150166","https://openalex.org/W4281490773","https://openalex.org/W4307323391","https://openalex.org/W4372341178","https://openalex.org/W4386811887","https://openalex.org/W4390075359","https://openalex.org/W4391021739","https://openalex.org/W4393241602","https://openalex.org/W4400064835","https://openalex.org/W6638749077","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6779753539","https://openalex.org/W6779919476","https://openalex.org/W6780179280","https://openalex.org/W6791346067","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6803861248","https://openalex.org/W6804171790","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6849683939","https://openalex.org/W6849983003","https://openalex.org/W6850224944","https://openalex.org/W6850334629","https://openalex.org/W6852343506","https://openalex.org/W6852581948","https://openalex.org/W6861267420","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2391251536","https://openalex.org/W2793058541","https://openalex.org/W2362198218","https://openalex.org/W1983629434","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W2375008505","https://openalex.org/W1982750869"],"abstract_inverted_index":{"We":[0],"present":[1],"SegINR,":[2],"a":[3,54,84],"novel":[4],"approach":[5],"to":[6],"neural":[7,57],"Text-to-Speech":[8],"(TTS)":[9],"that":[10,102],"eliminates":[11],"the":[12,29],"need":[13],"for":[14,25,91],"either":[15],"an":[16],"auxiliary":[17],"duration":[18],"predictor":[19],"or":[20],"autoregressive":[21],"(AR)":[22],"sequence":[23],"modeling":[24],"alignment.":[26],"SegINR":[27,88,103],"simplifies":[28],"TTS":[30,86,99],"process":[31],"by":[32],"directly":[33],"converting":[34],"text":[35,41],"sequences":[36],"into":[37,45,83],"frame-level":[38,48],"features.":[39],"Encoded":[40],"embeddings":[42],"are":[43],"transformed":[44],"segments":[46],"of":[47],"features":[49],"with":[50,110],"length":[51],"regulation":[52],"using":[53],"conditional":[55],"implicit":[56],"representation":[58],"(INR).":[59],"This":[60],"method,":[61],"termed":[62],"Segment-wise":[63],"INR":[64],"(SegINR),":[65],"captures":[66],"temporal":[67],"dynamics":[68],"within":[69],"each":[70],"segment":[71,75],"while":[72],"autonomously":[73],"defining":[74],"boundaries,":[76],"resulting":[77],"in":[78,96,107],"lower":[79],"computational":[80,111],"costs.":[81],"Integrated":[82],"two-stage":[85],"framework,":[87],"is":[89],"employed":[90],"semantic":[92],"token":[93],"prediction.":[94],"Experiments":[95],"zero-shot":[97],"adaptive":[98],"scenarios":[100],"show":[101],"outperforms":[104],"conventional":[105],"methods":[106],"speech":[108],"quality":[109],"efficiency.":[112]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}