{"id":"https://openalex.org/W4402402635","doi":"https://doi.org/10.1109/icasspw62465.2024.10669905","title":"High-Fidelity Neural Phonetic Posteriorgrams","display_name":"High-Fidelity Neural Phonetic Posteriorgrams","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4402402635","doi":"https://doi.org/10.1109/icasspw62465.2024.10669905"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10669905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10669905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5094040174","display_name":"Cameron Churchwell","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cameron Churchwell","raw_affiliation_strings":["Northwestern University,Evanston,IL,USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University,Evanston,IL,USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102779961","display_name":"Max Morrison","orcid":"https://orcid.org/0000-0002-6082-5157"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max Morrison","raw_affiliation_strings":["Northwestern University,Evanston,IL,USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University,Evanston,IL,USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878078","display_name":"Bryan Pardo","orcid":"https://orcid.org/0000-0002-1427-6492"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":["Northwestern University,Evanston,IL,USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University,Evanston,IL,USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5094040174"],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":2.6339,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90943296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"823","last_page":"827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7312312126159668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5299136638641357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3974505066871643},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36946016550064087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312312126159668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5299136638641357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3974505066871643},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36946016550064087}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10669905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10669905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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":33,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1682127088","https://openalex.org/W2079735306","https://openalex.org/W2147774191","https://openalex.org/W2171019095","https://openalex.org/W2518172956","https://openalex.org/W2747874407","https://openalex.org/W2973142754","https://openalex.org/W2998572311","https://openalex.org/W3036601975","https://openalex.org/W3082130377","https://openalex.org/W3083423753","https://openalex.org/W3165478005","https://openalex.org/W3206440620","https://openalex.org/W3207272747","https://openalex.org/W4293363567","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4318751639","https://openalex.org/W4319587015","https://openalex.org/W4372347381","https://openalex.org/W4372349390","https://openalex.org/W6603838645","https://openalex.org/W6739901393","https://openalex.org/W6761051331","https://openalex.org/W6771467084","https://openalex.org/W6772349387","https://openalex.org/W6780218876","https://openalex.org/W6796464841","https://openalex.org/W6810714412","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6849446024"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"A":[0],"phonetic":[1],"posteriorgram":[2],"(PPG)":[3],"is":[4],"a":[5,18,63],"time-varying":[6],"categorical":[7],"distribution":[8],"over":[9,86],"acoustic":[10,100],"units":[11],"of":[12,38,59,95],"speech":[13,22,72],"(e.g.,":[14,40,47],"phonemes).":[15],"PPGs":[16,60,82],"are":[17],"popular":[19],"representation":[20,77],"in":[21],"generation":[23],"due":[24],"to":[25,28,61],"their":[26],"ability":[27],"disentangle":[29],"pronunciation":[30,39,45,101,105],"features":[31],"from":[32],"speaker":[33],"identity,":[34],"allowing":[35],"accurate":[36],"reconstruction":[37],"voice":[41],"conversion)":[42],"and":[43,78,88,103],"coarse-grained":[44],"editing":[46],"foreign":[48],"accent":[49],"conversion).":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"demonstrably":[55],"improve":[56],"the":[57],"quality":[58],"produce":[62],"state-of-the-art":[64],"interpretable":[65],"PPG":[66,76],"representation.":[67],"We":[68,90],"train":[69],"an":[70,99],"off-the-shelf":[71],"synthesizer":[73],"using":[74],"our":[75],"show":[79],"that":[80],"high-quality":[81],"yield":[83],"independent":[84],"control":[85],"pitch":[87],"pronunciation.":[89],"further":[91],"demonstrate":[92],"novel":[93],"uses":[94],"PPGs,":[96],"such":[97],"as":[98],"distance":[102],"fine-grained":[104],"control.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}