{"id":"https://openalex.org/W1881463189","doi":"https://doi.org/10.1186/s13636-015-0064-7","title":"Advanced acoustic modelling techniques in MP3 speech recognition","display_name":"Advanced acoustic modelling techniques in MP3 speech recognition","publication_year":2015,"publication_date":"2015-07-27","ids":{"openalex":"https://openalex.org/W1881463189","doi":"https://doi.org/10.1186/s13636-015-0064-7","mag":"1881463189"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-015-0064-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0064-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0064-7","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0064-7","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073341046","display_name":"Michal Borsk\u00fd","orcid":"https://orcid.org/0000-0001-7908-5411"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Michal Borsky","raw_affiliation_strings":["Department of Circuit Theory, Czech Technical University, Technick\u00e1 2, Prague 6, 166 27, Czech Republic","Department of Circuit Theory, Czech Technical University, Prague 6, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Circuit Theory, Czech Technical University, Technick\u00e1 2, Prague 6, 166 27, Czech Republic","institution_ids":["https://openalex.org/I44504214"]},{"raw_affiliation_string":"Department of Circuit Theory, Czech Technical University, Prague 6, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039450310","display_name":"Petr Poll\u00e1k","orcid":"https://orcid.org/0000-0002-1533-4199"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Petr Pollak","raw_affiliation_strings":["Department of Circuit Theory, Czech Technical University, Technick\u00e1 2, Prague 6, 166 27, Czech Republic","Department of Circuit Theory, Czech Technical University, Prague 6, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Circuit Theory, Czech Technical University, Technick\u00e1 2, Prague 6, 166 27, Czech Republic","institution_ids":["https://openalex.org/I44504214"]},{"raw_affiliation_string":"Department of Circuit Theory, Czech Technical University, Prague 6, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040000490","display_name":"Petr Mizera","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Petr Mizera","raw_affiliation_strings":["Department of Circuit Theory, Czech Technical University, Technick\u00e1 2, Prague 6, 166 27, Czech Republic","Department of Circuit Theory, Czech Technical University, Prague 6, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Circuit Theory, Czech Technical University, Technick\u00e1 2, Prague 6, 166 27, Czech Republic","institution_ids":["https://openalex.org/I44504214"]},{"raw_affiliation_string":"Department of Circuit Theory, Czech Technical University, Prague 6, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073341046"],"corresponding_institution_ids":["https://openalex.org/I44504214"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.2943,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85313526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2015","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.9976999759674072,"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":0.816146731376648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8141152858734131},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7973280549049377},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.544313907623291},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4796364903450012},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4316962659358978},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.421924889087677},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.4162457287311554},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4134984612464905},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.41211628913879395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38332250714302063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3299359083175659},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32198089361190796},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07485881447792053}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.816146731376648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141152858734131},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7973280549049377},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.544313907623291},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4796364903450012},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4316962659358978},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.421924889087677},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.4162457287311554},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4134984612464905},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.41211628913879395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38332250714302063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3299359083175659},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32198089361190796},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07485881447792053},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s13636-015-0064-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0064-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0064-7","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s13636-015-0064-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-015-0064-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-015-0064-7","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1881463189.pdf","grobid_xml":"https://content.openalex.org/works/W1881463189.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W181598507","https://openalex.org/W191494004","https://openalex.org/W1486795655","https://openalex.org/W1510384566","https://openalex.org/W1519288196","https://openalex.org/W1524333225","https://openalex.org/W1911859126","https://openalex.org/W2018455158","https://openalex.org/W2100860879","https://openalex.org/W2112909784","https://openalex.org/W2117366609","https://openalex.org/W2151046578","https://openalex.org/W2171070222","https://openalex.org/W2277967659","https://openalex.org/W2299124942","https://openalex.org/W3134910092","https://openalex.org/W3185973041","https://openalex.org/W4302327898"],"related_works":["https://openalex.org/W2069501481","https://openalex.org/W2972436155","https://openalex.org/W2921683566","https://openalex.org/W1546240199","https://openalex.org/W2980451698","https://openalex.org/W2151365363","https://openalex.org/W2063862874","https://openalex.org/W2154415461","https://openalex.org/W1923241916","https://openalex.org/W642007152"],"abstract_inverted_index":{"The":[0,55,88,113,137],"automatic":[1],"recognition":[2,36,86,101],"of":[3,19,25,34,70,79,99,111,115,130,139],"MP3":[4,40],"compressed":[5,41],"speech":[6,27,42,85,105],"presents":[7],"a":[8,35,96,108,143],"challenge":[9],"to":[10,15,121],"the":[11,16,26,32,73,77,92,100,123,128,148,152,161],"current":[12,44],"systems":[13],"due":[14],"lossy":[17],"nature":[18],"compression":[20],"which":[21],"causes":[22],"irreversible":[23],"degradation":[24],"wave.":[28],"This":[29],"article":[30,56],"evaluates":[31],"performance":[33],"system":[37],"optimized":[38],"for":[39,72,103,147,160],"with":[43,134],"state-of-the-art":[45],"acoustic":[46,59,116],"modelling":[47],"techniques":[48],"and":[49,64,81],"one":[50],"specific":[51],"front-end":[52],"compensation":[53],"method.":[54],"concentrates":[57],"on":[58,91],"model":[60,117],"adaptation,":[61],"discriminative":[62,131],"training,":[63],"additional":[65,140],"dithering":[66,141],"as":[67,107],"prominent":[68],"means":[69],"compensating":[71],"described":[74],"distortion":[75],"in":[76],"task":[78,94],"phoneme":[80,93],"large":[82],"vocabulary":[83],"continuous":[84],"(LVCSR).":[87],"experiments":[89],"presented":[90],"show":[95],"dramatic":[97],"increase":[98],"error":[102],"unvoiced":[104],"units":[106],"direct":[109],"result":[110],"compression.":[112],"application":[114,138],"adaptation":[118],"has":[119],"proved":[120],"yield":[122],"highest":[124],"relative":[125],"contribution":[126],"while":[127],"gain":[129],"training":[132],"diminished":[133],"decreasing":[135],"bit-rate.":[136],"yielded":[142],"consistent":[144],"improvement":[145],"only":[146],"MFCC":[149],"features,":[150],"but":[151],"overall":[153],"results":[154],"were":[155],"still":[156],"worse":[157],"than":[158],"those":[159],"PLP":[162],"features.":[163]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
