{"id":"https://openalex.org/W2889417860","doi":"https://doi.org/10.21437/interspeech.2018-1487","title":"Whispered Speech to Neutral Speech Conversion Using Bidirectional LSTMs","display_name":"Whispered Speech to Neutral Speech Conversion Using Bidirectional LSTMs","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889417860","doi":"https://doi.org/10.21437/interspeech.2018-1487","mag":"2889417860"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1487","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5113010885","display_name":"G. Meenakshi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"G. Nisha Meenakshi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101685661","display_name":"Prasanta Kumar Ghosh","orcid":"https://orcid.org/0000-0002-1137-0838"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasanta Kumar Ghosh","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113010885"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3212,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.89613684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"495"},"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":0.9983999729156494,"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":0.9779000282287598,"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/speech-recognition","display_name":"Speech recognition","score":0.7842108011245728},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7544833421707153},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47636768221855164},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45610693097114563},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4238688051700592},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40854358673095703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3345567584037781},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0415206253528595}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7842108011245728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544833421707153},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47636768221855164},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45610693097114563},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4238688051700592},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40854358673095703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3345567584037781},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0415206253528595}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1487","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:62913","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2099105119","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W114661351","https://openalex.org/W4200596008","https://openalex.org/W596245619"],"abstract_inverted_index":{"We":[0,22,62,89,120],"propose":[1],"a":[2,24,85,188],"bidirectional":[3],"long":[4],"short-term":[5],"memory":[6],"(BLSTM)":[7],"based":[8,104,117],"whispered":[9,32,60,195],"speech":[10,13,20,33,193],"to":[11,26,34,44,66,110,133],"neutral":[12,37,192],"conversion":[14],"system":[15,105,130],"that":[16,91,111,123,161,183],"employs":[17],"the":[18,28,46,51,56,68,71,92,96,101,125,128,134,162,168,177,184],"STRAIGHT":[19],"synthesizer.":[21],"use":[23,63],"BLSTM":[25,103],"map":[27],"spectral":[29,57,73,97],"features":[30,58,74,98],"of":[31,36,59,70,95,127,145],"those":[35],"speech.":[38,61,196],"Three":[39],"other":[40],"BLSTMs":[41],"are":[42],"employed":[43],"predict":[45],"pitch,":[47],"periodicity":[48,151],"levels":[49],"and":[50,75,149],"voiced/unvoiced":[52],"phoneme":[53],"decisions":[54,148],"from":[55,81,194],"objective":[64],"measures":[65],"quantify":[67],"quality":[69],"predicted":[72,99,112],"excitation":[76],"parameters,":[77],"using":[78,100,113],"data":[79],"recorded":[80],"six":[82],"subjects,":[83],"in":[84,143],"four":[86],"fold":[87],"setup.":[88],"find":[90,160],"temporal":[93],"smoothness":[94],"proposed":[102,129,163,185],"is":[106,131,141,165],"statistically":[107],"more":[108,174,189],"compared":[109],"deep":[114],"neural":[115],"network":[116],"baseline":[118,135,179],"schemes.":[119],"also":[121],"observe":[122],"while":[124],"performance":[126],"comparable":[132],"scheme":[136,171],"for":[137],"pitch":[138],"prediction,":[139],"it":[140],"superior":[142],"terms":[144],"classifying":[146],"voicing":[147],"predicting":[150],"levels.":[152],"From":[153],"subjective":[154],"evaluation":[155],"via":[156],"listening":[157],"test,":[158],"we":[159],"method":[164,186],"chosen":[166],"as":[167],"best":[169,178],"performing":[170],"26.61%":[172],"(absolute)":[173],"often":[175],"than":[176],"scheme.":[180],"This":[181],"reveals":[182],"yields":[187],"natural":[190],"sounding":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}