{"id":"https://openalex.org/W4405709323","doi":"https://doi.org/10.1109/iscslp63861.2024.10800188","title":"Wav2f0: Exploring the Potential of Wav2vec 2.0 for Speech Fundamental Frequency Extraction","display_name":"Wav2f0: Exploring the Potential of Wav2vec 2.0 for Speech Fundamental Frequency Extraction","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709323","doi":"https://doi.org/10.1109/iscslp63861.2024.10800188"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800188","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/A5035671169","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0003-3345-5733"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Feng","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051501323","display_name":"Yin-Long Liu","orcid":"https://orcid.org/0009-0004-0380-0836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin-Long Liu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069176378","display_name":"Zhen-Hua Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043406907","display_name":"Jiahong Yuan","orcid":"https://orcid.org/0009-0008-2162-7167"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia-Hong Yuan","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035671169"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6632,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76944962,"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":"169","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9940999746322632,"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":0.9940999746322632,"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":0.917900025844574,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9108999967575073,"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":0.6419933438301086},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.5656678080558777},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5394582748413086},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4563910961151123},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21946361660957336},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1527877151966095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6419933438301086},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.5656678080558777},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5394582748413086},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4563910961151123},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21946361660957336},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1527877151966095},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800188","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1975079546","https://openalex.org/W2020820584","https://openalex.org/W2030582787","https://openalex.org/W2084044763","https://openalex.org/W2088632109","https://openalex.org/W2091425152","https://openalex.org/W2118774185","https://openalex.org/W2135431242","https://openalex.org/W2138039466","https://openalex.org/W2171321863","https://openalex.org/W2397375888","https://openalex.org/W2518618011","https://openalex.org/W2962866891","https://openalex.org/W3011176162","https://openalex.org/W4386702815","https://openalex.org/W6687133601","https://openalex.org/W6780218876","https://openalex.org/W6852880504"],"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":{"Speech":[0],"fundamental":[1,29],"frequency":[2,30],"(F0)":[3],"extraction":[4,80],"is":[5,101],"one":[6],"of":[7,23,69,99],"the":[8,21,36,47,83],"most":[9],"important":[10],"tasks":[11],"in":[12,78,86],"speech":[13,28],"signal":[14],"processing.":[15],"This":[16],"paper":[17],"aims":[18],"to":[19,91,111],"explore":[20],"feasibility":[22],"using":[24],"deep":[25],"learning":[26],"for":[27],"extraction.":[31],"Our":[32],"approach,":[33],"Wav2f0,":[34],"combines":[35],"Wav2vec":[37,52],"2.0":[38],"model":[39],"with":[40],"fully":[41],"connected":[42],"and":[43,57,72],"LSTM":[44],"layers,":[45],"leveraging":[46],"pretrained":[48],"representations":[49],"learned":[50],"by":[51],"2.0.":[53],"We":[54],"conduct":[55],"training":[56],"evaluation":[58],"on":[59,82],"a":[60,104],"Vietnamese":[61],"tone":[62],"production":[63],"corpus,":[64,84],"which":[65],"contains":[66],"parallel":[67],"recordings":[68],"Electroglottograph":[70],"(EGG)":[71],"microphone":[73],"signals.":[74],"Wav2f0":[75,100],"outperforms":[76],"Praat":[77,89],"pitch":[79],"accuracy":[81],"especially":[85],"scenarios":[87],"where":[88],"fails":[90],"estimate":[92],"pitch.":[93],"The":[94],"Gross":[95],"Pitch":[96],"Error":[97],"(GPE)":[98],"7.1%,":[102],"representing":[103],"more":[105],"than":[106],"50%":[107],"error":[108],"reduction":[109],"compared":[110],"Praat's":[112],"15.5%.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}