{"id":"https://openalex.org/W2793105386","doi":"https://doi.org/10.21105/joss.00749","title":"SpeechPy - A Library for Speech Processing and Recognition","display_name":"SpeechPy - A Library for Speech Processing and Recognition","publication_year":2018,"publication_date":"2018-07-23","ids":{"openalex":"https://openalex.org/W2793105386","doi":"https://doi.org/10.21105/joss.00749","mag":"2793105386"},"language":"en","primary_location":{"id":"doi:10.21105/joss.00749","is_oa":true,"landing_page_url":"http://doi.org/10.21105/joss.00749","pdf_url":"https://doi.org/10.21105/joss.00749","source":{"id":"https://openalex.org/S4210214273","display_name":"The Journal of Open Source Software","issn_l":"2475-9066","issn":["2475-9066"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315853","host_organization_name":"Open Journals","host_organization_lineage":["https://openalex.org/P4310315853"],"host_organization_lineage_names":["Open Journals"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Source Software","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.21105/joss.00749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064784351","display_name":"Amirsina Torfi","orcid":"https://orcid.org/0000-0003-2282-4361"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amirsina Torfi","raw_affiliation_strings":["Department of Computer Science Virginia Tech"],"raw_orcid":"https://orcid.org/0000-0003-2282-4361","affiliations":[{"raw_affiliation_string":"Department of Computer Science Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5064784351"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":1.0154,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.82077599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":"27","first_page":"749","last_page":"749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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":0.8056786060333252},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7624865770339966},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7345440983772278},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.662621021270752},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6388616561889648},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.631254255771637},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5372097492218018},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5085796117782593},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43074262142181396},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41968071460723877},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.40790635347366333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3475089967250824},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0778103768825531}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8056786060333252},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7624865770339966},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7345440983772278},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.662621021270752},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6388616561889648},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.631254255771637},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5372097492218018},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5085796117782593},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43074262142181396},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41968071460723877},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.40790635347366333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3475089967250824},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0778103768825531},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21105/joss.00749","is_oa":true,"landing_page_url":"http://doi.org/10.21105/joss.00749","pdf_url":"https://doi.org/10.21105/joss.00749","source":{"id":"https://openalex.org/S4210214273","display_name":"The Journal of Open Source Software","issn_l":"2475-9066","issn":["2475-9066"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315853","host_organization_name":"Open Journals","host_organization_lineage":["https://openalex.org/P4310315853"],"host_organization_lineage_names":["Open Journals"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Source Software","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1803.01094","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.01094","pdf_url":"https://arxiv.org/pdf/1803.01094","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.21105/joss.00749","is_oa":true,"landing_page_url":"http://doi.org/10.21105/joss.00749","pdf_url":"https://doi.org/10.21105/joss.00749","source":{"id":"https://openalex.org/S4210214273","display_name":"The Journal of Open Source Software","issn_l":"2475-9066","issn":["2475-9066"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315853","host_organization_name":"Open Journals","host_organization_lineage":["https://openalex.org/P4310315853"],"host_organization_lineage_names":["Open Journals"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Open Source Software","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2793105386.pdf","grobid_xml":"https://content.openalex.org/works/W2793105386.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1560013842","https://openalex.org/W1922017469","https://openalex.org/W1984541135","https://openalex.org/W1994396704","https://openalex.org/W2041404167","https://openalex.org/W2046056978","https://openalex.org/W2107789863","https://openalex.org/W2123237149","https://openalex.org/W2124397839","https://openalex.org/W2129244720","https://openalex.org/W2151484683","https://openalex.org/W2160815625","https://openalex.org/W2192412620","https://openalex.org/W2618829015","https://openalex.org/W2734984521","https://openalex.org/W2789135445","https://openalex.org/W2919115771","https://openalex.org/W2964307722","https://openalex.org/W2978725006","https://openalex.org/W2981022124","https://openalex.org/W3105440745","https://openalex.org/W4295369237","https://openalex.org/W6894286645"],"related_works":["https://openalex.org/W2186375278","https://openalex.org/W2114026179","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2108641942","https://openalex.org/W2355290951","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805"],"abstract_inverted_index":{"SpeechPy":[0],"is":[1,41],"an":[2],"open":[3],"source":[4],"Python":[5],"package":[6,40],"that":[7],"contains":[8],"speech":[9,12,23,50],"preprocessing":[10],"techniques,":[11],"features,":[13],"and":[14,27,53,63],"important":[15],"post-processing":[16],"operations.":[17],"It":[18],"provides":[19],"most":[20],"frequent":[21],"used":[22],"features":[24],"including":[25],"MFCCs":[26],"filterbank":[28],"energies":[29],"alongside":[30],"with":[31,45],"the":[32,39],"log-energy":[33],"of":[34,38],"filter-banks.":[35],"The":[36],"aim":[37],"to":[42],"provide":[43],"researchers":[44],"a":[46],"simple":[47],"tool":[48],"for":[49],"feature":[51],"extraction":[52],"processing":[54],"purposes":[55],"in":[56],"applications":[57],"such":[58],"as":[59],"Automatic":[60],"Speech":[61],"Recognition":[62],"Speaker":[64],"Verification.":[65]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
