{"id":"https://openalex.org/W4408354018","doi":"https://doi.org/10.1109/icassp49660.2025.10887580","title":"HamaraAwaz: Advancing Low-Latency Streaming TTS for Multilingual Speech in Indian Languages","display_name":"HamaraAwaz: Advancing Low-Latency Streaming TTS for Multilingual Speech in Indian Languages","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354018","doi":"https://doi.org/10.1109/icassp49660.2025.10887580"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887580","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/A5101799872","display_name":"Neil Shah","orcid":"https://orcid.org/0000-0003-3261-8430"},"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":"Neil Shah","raw_affiliation_strings":["IIIT Hyderabad,CVIT,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,CVIT,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093307080","display_name":"Parth Khadse","orcid":"https://orcid.org/0009-0003-4321-6936"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parth Khadse","raw_affiliation_strings":["TCS Research,Mumbai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research,Mumbai,India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071297635","display_name":"Shirish Karande","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shirish Karande","raw_affiliation_strings":["TCS Research,Pune,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research,Pune,India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047383705","display_name":"Sunil Kumar Kopparapu","orcid":"https://orcid.org/0000-0002-0502-527X"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunil Kumar Kopparapu","raw_affiliation_strings":["TCS Research,Mumbai,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research,Mumbai,India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85583395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9958000183105469,"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":0.9958000183105469,"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":0.9753999710083008,"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/T12031","display_name":"Speech and dialogue systems","score":0.9613999724388123,"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":0.7904229164123535},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5490440130233765},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.5399605631828308},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47172799706459045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32216498255729675},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12153112888336182},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10655036568641663}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904229164123535},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5490440130233765},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.5399605631828308},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47172799706459045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32216498255729675},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12153112888336182},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10655036568641663}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887580","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2963250244","https://openalex.org/W2963925437","https://openalex.org/W6783867762","https://openalex.org/W6810419249"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W4308600690"],"abstract_inverted_index":{"We":[0,34],"present":[1],"a":[2,65,74],"multilingual,":[3],"multi-speaker,":[4],"low-latency":[5],"speech":[6,38,59],"synthesis":[7],"system":[8],"developed":[9],"by":[10],"the":[11,18,81],"HamaraAwaz":[12],"team":[13],"for":[14,47],"Track":[15],"1":[16],"of":[17,71,78,88],"LIMMITS\u201925":[19,82],"challenge.":[20],"To":[21],"improve":[22],"speaker":[23,75],"similarity":[24,76],"and":[25,40,53,73],"naturalness":[26,66],"in":[27,80],"Indic":[28],"languages,":[29],"we":[30],"build":[31],"on":[32],"ParrotTTS.":[33],"utilize":[35],"disentangled":[36],"self-supervised":[37],"representations":[39,56],"incorporate":[41],"enhancements":[42],"such":[43],"as":[44,86],"Byte-Pair":[45],"Encoding":[46],"text":[48],"representation":[49],"to":[50,57],"reduce":[51],"latency":[52],"relative":[54],"positional":[55],"enhance":[58],"quality.":[60],"The":[61],"proposed":[62],"model":[63],"achieved":[64],"Mean":[67],"Opinion":[68],"Score":[69],"(MOS)":[70],"3.51":[72],"score":[77],"3.53":[79],"grand":[83],"challenge":[84],"held":[85],"part":[87],"ICASSP-25.":[89],"Speech":[90],"samples":[91],"are":[92],"available":[93],"at":[94],"https://parrot-tts.github.io/HamaraAwaz/":[95]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
