{"id":"https://openalex.org/W4408352714","doi":"https://doi.org/10.1109/icassp49660.2025.10890273","title":"Stream-TTS: A Low-Latency Text-to-Speech using Kolmogorov-Arnold Networks for Streaming Speech Applications","display_name":"Stream-TTS: A Low-Latency Text-to-Speech using Kolmogorov-Arnold Networks for Streaming Speech Applications","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352714","doi":"https://doi.org/10.1109/icassp49660.2025.10890273"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5065642629","display_name":"Giridhar Pamisetty","orcid":"https://orcid.org/0000-0001-5945-6860"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Giridhar Pamisetty","raw_affiliation_strings":["Indian Institute of Technology Hyderabad,Speech Information Processing Lab,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad,Speech Information Processing Lab,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594364","display_name":"Riya Ann Easow","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Riya Ann Easow","raw_affiliation_strings":["Indian Institute of Technology Hyderabad,Speech Information Processing Lab,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad,Speech Information Processing Lab,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021991292","display_name":"Kaustubh Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kaustubh Gupta","raw_affiliation_strings":["Indian Institute of Technology Hyderabad,Speech Information Processing Lab,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad,Speech Information Processing Lab,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067617924","display_name":"K. Sri Rama Murty","orcid":"https://orcid.org/0000-0002-6355-5287"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K Sri Rama Murty","raw_affiliation_strings":["Indian Institute of Technology Hyderabad,Speech Information Processing Lab,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Hyderabad,Speech Information Processing Lab,India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065642629"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":3.1318,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90136716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9861000180244446,"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":0.9861000180244446,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9642000198364258,"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/T12031","display_name":"Speech and dialogue systems","score":0.902899980545044,"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/computer-science","display_name":"Computer science","score":0.7539269328117371},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5536410212516785},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5523276925086975},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4186321496963501},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13780000805854797}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539269328117371},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5536410212516785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5523276925086975},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4186321496963501},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13780000805854797}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3203313352","https://openalex.org/W4328054451","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"The":[0,96],"rise":[1],"of":[2,33,58,109,117,130],"conversational":[3],"AI":[4],"and":[5,45,111],"multimodal":[6],"streaming":[7,124],"applications":[8],"has":[9],"led":[10],"to":[11,88],"a":[12,23,65,84,100,105,112],"significant":[13],"demand":[14],"for":[15,119],"low-latency":[16,25],"Text-to-Speech":[17],"(TTS)":[18],"systems.":[19],"This":[20],"work":[21],"presents":[22],"multilingual":[24,123],"model":[26,98],"that":[27],"leverages":[28],"the":[29,39,55,59,79,90,94,122],"functional":[30],"decomposition":[31],"principles":[32],"Kolmogorov-Arnold":[34],"Networks":[35],"(KANs)":[36],"in":[37,121],"modeling":[38],"nonlinear":[40,86],"functions":[41],"with":[42,70,104],"lesser":[43],"parameters":[44],"smaller":[46],"computational":[47],"graphs":[48],"than":[49],"multi-layer":[50],"perceptrons":[51],"(MLPs).":[52],"To":[53],"enhance":[54],"learning":[56,68],"capabilities":[57],"proposed":[60,97],"compact":[61],"model,":[62],"we":[63],"use":[64,83],"supervised":[66],"auxiliary":[67],"approach":[69],"multiple":[71],"subtasks":[72],"whose":[73],"target":[74],"labels":[75],"are":[76],"extracted":[77],"from":[78,93],"speech":[80,92],"signal.":[81],"We":[82],"multispeaker":[85],"vocoder":[87],"reconstruct":[89],"natural-sounding":[91],"Melspectrograms.":[95],"achieved":[99],"very":[101],"low":[102],"latency":[103],"real-time":[106],"factor":[107],"(RTF)":[108],"0.0795":[110],"mean":[113],"opinion":[114],"score":[115],"(MOS)":[116],"4.09":[118],"naturalness":[120],"TTS":[125],"challenge":[126],"organized":[127],"as":[128],"part":[129],"ICASSP-2025.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}