{"id":"https://openalex.org/W4405709306","doi":"https://doi.org/10.1109/iscslp63861.2024.10800697","title":"The NPU-HWC System for the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge","display_name":"The NPU-HWC System for the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709306","doi":"https://doi.org/10.1109/iscslp63861.2024.10800697"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5101377824","display_name":"Dake Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dake Guo","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jixun Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixun Yao","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kangxiang Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangxiang Xia","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102666137","display_name":"Zhao Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Guo","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100706047","display_name":"Ziyu Zhang","orcid":"https://orcid.org/0000-0001-9000-4555"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Zhang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695538","display_name":"Yao Wang","orcid":"https://orcid.org/0000-0003-2480-3660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Wang","raw_affiliation_strings":["Huawei Cloud"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029890362","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0001-8424-5184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Huawei Cloud"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi'an","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6114,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68450898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"616","last_page":"620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9822999835014343,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9822999835014343,"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/T11309","display_name":"Music and Audio Processing","score":0.9797000288963318,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9440000057220459,"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":0.5626606941223145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5626606941223145}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":29,"referenced_works":["https://openalex.org/W2939913319","https://openalex.org/W2963609956","https://openalex.org/W3163132306","https://openalex.org/W3196584150","https://openalex.org/W3200756692","https://openalex.org/W4283067311","https://openalex.org/W4297841574","https://openalex.org/W4372346850","https://openalex.org/W4391833199","https://openalex.org/W4402111239","https://openalex.org/W4402111455","https://openalex.org/W4402112533","https://openalex.org/W4403780831","https://openalex.org/W4405709275","https://openalex.org/W6763832098","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6810334672","https://openalex.org/W6845479124","https://openalex.org/W6847076894","https://openalex.org/W6848735303","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6851724922","https://openalex.org/W6852418670","https://openalex.org/W6852421699","https://openalex.org/W6854199242","https://openalex.org/W6857478255","https://openalex.org/W6869301554"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0,114],"paper":[1],"presents":[2],"the":[3,8,47,72,76,81,130,141,145],"NPU-HWC":[4],"system":[5,20,115],"submitted":[6],"to":[7,45,57,89,94],"ISCSLP":[9],"2024":[10,17],"Inspirational":[11],"and":[12,31,52,68,126,144,151],"Convincing":[13],"Audio":[14],"Generation":[15],"Challenge":[16],"(ICAGC).":[18],"Our":[19,138],"consists":[21],"of":[22],"two":[23],"modules:":[24],"a":[25,32,54,104],"speech":[26,48,131],"generator":[27,35],"for":[28,36],"Track":[29,37,40,100,135,149,152],"1":[30,136,150],"background":[33,105,121],"audio":[34,106,122],"2.":[38],"In":[39,99],"1,":[41],"we":[42,86,102],"employ":[43],"Single-Codec":[44,64],"tokenize":[46],"into":[49],"discrete":[50],"tokens":[51],"use":[53,87],"language-model-based":[55],"approach":[56],"achieve":[58],"zero-shot":[59],"speaking":[60,69],"style":[61,70],"cloning.":[62],"The":[63],"effectively":[65],"decouples":[66],"timbre":[67],"at":[71],"token":[73],"level,":[74],"reducing":[75],"acoustic":[77],"modeling":[78],"burden":[79],"on":[80,109],"autoregressive":[82],"language":[83,111],"model.":[84],"Additionally,":[85],"DSPGAN":[88],"upsample":[90],"16":[91],"kHz":[92,97],"mel-spectrograms":[93],"high-fidelity":[95],"48":[96],"waveforms.":[98],"2,":[101,125],"propose":[103],"gen-erator":[107],"based":[108],"large":[110],"models":[112],"(LLMs).":[113],"produces":[116],"scene-appropriate":[117],"accompaniment":[118],"descriptions,":[119],"synthesizes":[120],"with":[123,129],"Tango":[124],"integrates":[127],"it":[128],"generated":[132],"by":[133],"our":[134],"system.":[137],"submission":[139],"achieves":[140],"second":[142],"place":[143,147],"first":[146],"in":[148],"2":[153],"respectively.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}