{"id":"https://openalex.org/W7125805795","doi":"https://doi.org/10.1016/j.specom.2026.103353","title":"Emphasis rendering for conversational text-to-speech with multi-modal multi-scale context modeling","display_name":"Emphasis rendering for conversational text-to-speech with multi-modal multi-scale context modeling","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125805795","doi":"https://doi.org/10.1016/j.specom.2026.103353"},"language":"en","primary_location":{"id":"doi:10.1016/j.specom.2026.103353","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103353","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","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/A5123968404","display_name":"Rui Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Liu","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, 010021, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, 010021, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123904627","display_name":"Jia Zhenqi","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Zhenqi","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, 010021, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, 010021, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124034044","display_name":"Jie Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, 010021, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, 010021, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123971365","display_name":"Yifan Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Hu","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, 010021, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, 010021, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123923912","display_name":"Haizhou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["School of Artificial Intelligence, School of Data Science, SRIBD, The Chinese University of Hong Kong, Shenzhen, 518172, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, School of Data Science, SRIBD, The Chinese University of Hong Kong, Shenzhen, 518172, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5123968404"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":{"value":2870,"currency":"USD","value_usd":2870},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30027981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"178","issue":null,"first_page":"103353","last_page":"103353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6679999828338623,"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":0.6679999828338623,"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":0.11219999939203262,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.08150000125169754,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/emphasis","display_name":"Emphasis (telecommunications)","score":0.920199990272522},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6193000078201294},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5960000157356262},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5813999772071838},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41659998893737793},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.400299996137619}],"concepts":[{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.920199990272522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8539999723434448},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6193000078201294},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5813999772071838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44110000133514404},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40310001373291016},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.400299996137619},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.specom.2026.103353","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103353","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5561957955360413}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1975163393","https://openalex.org/W2144578941","https://openalex.org/W2146334809","https://openalex.org/W2591082262","https://openalex.org/W2747874407","https://openalex.org/W2888855092","https://openalex.org/W2953061889","https://openalex.org/W2970641574","https://openalex.org/W2985882473","https://openalex.org/W3159367349","https://openalex.org/W4281397735","https://openalex.org/W4304013787","https://openalex.org/W4313828967","https://openalex.org/W4385486424","https://openalex.org/W4387968649","https://openalex.org/W4390480998","https://openalex.org/W4392903647","https://openalex.org/W4393160807","https://openalex.org/W4393372125","https://openalex.org/W4406560414","https://openalex.org/W4409348122","https://openalex.org/W4415481591","https://openalex.org/W4415536841","https://openalex.org/W4415540092","https://openalex.org/W4416036598"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-02-02T03:55:41.653505","created_date":"2026-01-28T00:00:00"}
