{"id":"https://openalex.org/W2261475161","doi":"https://doi.org/10.3115/v1/n15-1148","title":"GPU-Friendly Local Regression for Voice Conversion","display_name":"GPU-Friendly Local Regression for Voice Conversion","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2261475161","doi":"https://doi.org/10.3115/v1/n15-1148","mag":"2261475161"},"language":"en","primary_location":{"id":"doi:10.3115/v1/n15-1148","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/n15-1148","pdf_url":"https://www.aclweb.org/anthology/N15-1148.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/N15-1148.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Computer Science Division University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004921249","display_name":"Dan Klein","orcid":"https://orcid.org/0000-0002-8881-1902"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dan Klein","raw_affiliation_strings":["Computer Science Division University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Computer Science Division University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004921249"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0900885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1334","last_page":"1338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.998199999332428,"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":0.8292629718780518},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6895533204078674},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6264248490333557},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6263858079910278},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.53904789686203},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49639636278152466},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.43355798721313477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32591474056243896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1731168031692505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292629718780518},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6895533204078674},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6264248490333557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6263858079910278},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.53904789686203},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49639636278152466},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.43355798721313477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32591474056243896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1731168031692505},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/n15-1148","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/n15-1148","pdf_url":"https://www.aclweb.org/anthology/N15-1148.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.707.367","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.707.367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/%7Etberg/papers/naacl2015.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/n15-1148","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/n15-1148","pdf_url":"https://www.aclweb.org/anthology/N15-1148.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2261475161.pdf","grobid_xml":"https://content.openalex.org/works/W2261475161.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2005438552","https://openalex.org/W2024081693","https://openalex.org/W2028499920","https://openalex.org/W2110118271","https://openalex.org/W2114659828","https://openalex.org/W2120605154","https://openalex.org/W2152205330","https://openalex.org/W2156142001","https://openalex.org/W4253016408"],"related_works":["https://openalex.org/W31220157","https://openalex.org/W2312753042","https://openalex.org/W4289356671","https://openalex.org/W2389155397","https://openalex.org/W2165884543","https://openalex.org/W3186837933","https://openalex.org/W2368989808","https://openalex.org/W1969346022","https://openalex.org/W2034959125","https://openalex.org/W2355687852"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,29],"is":[2,31,57,70,80,92],"the":[3,76],"task":[4],"of":[5,33],"transforming":[6],"a":[7,16,22,48,65,86],"source":[8],"speaker's":[9,18],"voice":[10,28],"so":[11],"that":[12,30,56],"it":[13],"sounds":[14],"like":[15],"target":[17],"voice.":[19],"We":[20],"present":[21],"GPUfriendly":[23],"local":[24,53],"regression":[25,54],"model":[26,46],"for":[27,51],"capable":[32],"converting":[34],"speech":[35,96],"in":[36],"real-time":[37],"and":[38,91],"achieves":[39],"state-of-the-art":[40],"accuracy":[41],"on":[42,75],"this":[43],"task.":[44],"Our":[45,78],"uses":[47],"new":[49],"approximation":[50],"computing":[52],"coefficients":[55],"explicitly":[58],"designed":[59],"to":[60,72,94],"preserve":[61],"memory":[62],"locality.":[63],"As":[64],"result,":[66],"our":[67],"inference":[68],"procedure":[69],"amenable":[71],"efficient":[73],"implementation":[74],"GPU.":[77],"approach":[79],"more":[81],"than":[82,85,99],"10X":[83],"faster":[84,98],"highly":[87],"optimized":[88],"CPUbased":[89],"implementation,":[90],"able":[93],"convert":[95],"2.7X":[97],"real-time.":[100]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}