{"id":"https://openalex.org/W4226230180","doi":"https://doi.org/10.21437/interspeech.2022-11171","title":"Towards Multi-Scale Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis","display_name":"Towards Multi-Scale Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226230180","doi":"https://doi.org/10.21437/interspeech.2022-11171"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11171","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11171","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5103014224","display_name":"Shun Lei","orcid":"https://orcid.org/0000-0003-3597-3913"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shun Lei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749226","display_name":"Yixuan Zhou","orcid":"https://orcid.org/0009-0002-6363-891X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixuan Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849127","display_name":"Liyang Chen","orcid":"https://orcid.org/0000-0001-6985-8281"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liyang Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075234257","display_name":"Jiankun Hu","orcid":"https://orcid.org/0000-0003-0230-1432"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiankun Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103014224"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1427,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79449472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9930999875068665,"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":0.9930999875068665,"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":0.9290000200271606,"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":0.9126999974250793,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.86372309923172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.726091742515564},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6973426342010498},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.630046010017395},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5713567733764648},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5284309983253479},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5280523896217346},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4637143611907959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38210272789001465},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3605380654335022},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.08374989032745361},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07602870464324951}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.86372309923172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.726091742515564},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6973426342010498},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.630046010017395},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5713567733764648},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5284309983253479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5280523896217346},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4637143611907959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38210272789001465},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3605380654335022},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08374989032745361},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07602870464324951},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11171","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11171","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2050927497","https://openalex.org/W2050631214","https://openalex.org/W24638226","https://openalex.org/W2380871027","https://openalex.org/W2146639687","https://openalex.org/W321531528","https://openalex.org/W2106564373","https://openalex.org/W2922185715","https://openalex.org/W2008272336","https://openalex.org/W2046566646"],"abstract_inverted_index":{"Previous":[0],"works":[1],"on":[2,7,87,96],"expressive":[3],"speech":[4,28],"synthesis":[5],"focus":[6],"modelling":[8,40],"the":[9,14,20,51,73,79,109,114],"mono-scale":[10],"style":[11,25,39,48,66,84],"embedding":[12],"from":[13,72],"current":[15],"sentence":[16],"or":[17],"context,":[18],"but":[19],"multi-scale":[21,37,46,59,83],"nature":[22],"of":[23,55,81,113],"speaking":[24,38,47,65],"in":[26],"human":[27],"is":[29,61],"neglected.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"propose":[35],"a":[36,82,97],"method":[41,105],"to":[42,63],"capture":[43],"and":[44,53,76,93,111],"predict":[45],"for":[49],"improving":[50],"naturalness":[52,110],"expressiveness":[54,112],"synthetic":[56],"speech.":[57,116],"A":[58],"extractor":[60],"proposed":[62,104],"extract":[64],"embeddings":[67],"at":[68],"three":[69],"different":[70],"levels":[71],"ground-truth":[74],"speech,":[75],"explicitly":[77],"guide":[78],"training":[80],"predictor":[85],"based":[86],"hierarchical":[88],"context":[89],"information.":[90],"Both":[91],"objective":[92],"subjective":[94],"evaluations":[95],"Mandarin":[98],"audiobooks":[99],"dataset":[100],"demonstrate":[101],"that":[102],"our":[103],"can":[106],"significantly":[107],"improve":[108],"synthesized":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}