{"id":"https://openalex.org/W6888583628","doi":"https://doi.org/10.21227/5vgy-yb08","title":"Speech Dataset in Hindi Language","display_name":"Speech Dataset in Hindi Language","publication_year":2020,"publication_date":"2020-06-09","ids":{"openalex":"https://openalex.org/W6888583628","doi":"https://doi.org/10.21227/5vgy-yb08"},"language":"en","primary_location":{"id":"doi:10.21227/5vgy-yb08","is_oa":true,"landing_page_url":"https://doi.org/10.21227/5vgy-yb08","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/5vgy-yb08","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shukla, Shivam","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shukla, Shivam","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5817000269889832},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5590000152587891},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5170000195503235},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.3562999963760376},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3424000144004822},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.32749998569488525},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.30799999833106995}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7005000114440918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6581000089645386},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5817000269889832},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5590000152587891},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4569000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3562999963760376},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C89051679","wikidata":"https://www.wikidata.org/wiki/Q627770","display_name":"Voice-onset time","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28299999237060547},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.26589998602867126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/5vgy-yb08","is_oa":true,"landing_page_url":"https://doi.org/10.21227/5vgy-yb08","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.21227/5vgy-yb08","is_oa":true,"landing_page_url":"https://doi.org/10.21227/5vgy-yb08","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"100":[0],"Speakers":[1],"each":[2],"consisting":[3],"of":[4,19,51,59,94],"5":[5],"voice":[6,13,21,45],"samples":[7,22,35],"for":[8,15,83],"training":[9],"data":[10,95],"and":[11,39,71],"1":[12,74],"sample":[14,46],"testing":[16],"data.":[17],"Total":[18],"600":[20],"collected":[23],"in":[24],"different":[25,56],"audio":[26],"formats":[27],"like":[28],"mpeg,":[29],"mp4,":[30],"mp3,":[31],"ogg":[32],"etc.":[33,92],"These":[34],"were":[36],"than":[37],"preprocessed":[38],"converted":[40],"into":[41],".wav":[42],"format.":[43],"Each":[44],"has":[47],"a":[48],"time":[49],"duration":[50,72],"5-10":[52],"seconds":[53],"due":[54],"to":[55],"lengths":[57],"tuning":[58],"parameters":[60],"should":[61],"be":[62,81],"done":[63],"before":[64],"usage.":[65],"Whole":[66],"Dataset":[67],"size":[68],"is":[69,73,96],"600mb":[70],"hour":[75],"40":[76],"minutes.":[77],"This":[78],"dataset":[79],"can":[80],"used":[82],"speech":[84,90],"synthesis,":[85],"speaker":[86,88],"identification.":[87],"recognition,":[89],"recogniton":[91],"Preprocessing":[93],"required.":[97]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}