{"id":"https://openalex.org/W3015726069","doi":"https://doi.org/10.1109/icassp40776.2020.9053573","title":"The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment","display_name":"The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015726069","doi":"https://doi.org/10.1109/icassp40776.2020.9053573","mag":"3015726069"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100636970","display_name":"Wei Zhou","orcid":"https://orcid.org/0009-0006-3754-8872"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029547617","display_name":"Wilfried Michel","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wilfried Michel","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002810304","display_name":"Kazuki Irie","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kazuki Irie","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049536890","display_name":"Markus Kitza","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Kitza","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schluter","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100636970"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":5.9652,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96900287,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7839","last_page":"7843"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8788895606994629},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7830982208251953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7782468795776367},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6700769662857056},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.604602038860321},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5678256750106812},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5555219054222107},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.523885190486908},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.478059321641922},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.470943808555603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46881866455078125},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.46184131503105164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3439388573169708},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19046321511268616},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16125044226646423},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09080237150192261},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06055346131324768}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8788895606994629},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7830982208251953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782468795776367},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6700769662857056},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.604602038860321},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5678256750106812},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5555219054222107},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.523885190486908},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.478059321641922},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.470943808555603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46881866455078125},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.46184131503105164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3439388573169708},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19046321511268616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16125044226646423},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09080237150192261},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06055346131324768},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1934041838","https://openalex.org/W2024200390","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2110798204","https://openalex.org/W2158195707","https://openalex.org/W2251321385","https://openalex.org/W2398887489","https://openalex.org/W2402268235","https://openalex.org/W2471933213","https://openalex.org/W2782451907","https://openalex.org/W2902786662","https://openalex.org/W2903382683","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2944255943","https://openalex.org/W2956159074","https://openalex.org/W2962728618","https://openalex.org/W2963250244","https://openalex.org/W2963351448","https://openalex.org/W2963403868","https://openalex.org/W2972692349","https://openalex.org/W2972818416","https://openalex.org/W2973201641","https://openalex.org/W2989819126","https://openalex.org/W3007328579","https://openalex.org/W3008191852","https://openalex.org/W3103005696","https://openalex.org/W4288021071","https://openalex.org/W4288290348","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6674330103","https://openalex.org/W6676481782","https://openalex.org/W6691770337","https://openalex.org/W6739901393","https://openalex.org/W6747836893","https://openalex.org/W6757107679","https://openalex.org/W6765658108","https://openalex.org/W6770980983","https://openalex.org/W6887576000"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W4287644835","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W3092281475","https://openalex.org/W2033669961","https://openalex.org/W2971899271"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,8,91],"complete":[3],"training":[4,62,67],"pipeline":[5],"to":[6,29,70],"build":[7],"state-of-the-art":[9,102],"hybrid":[10,54],"HMM-based":[11],"ASR":[12],"system":[13,89],"on":[14,32,53,94],"the":[15,19,43,72,95,100],"2nd":[16],"release":[17],"of":[18,34,45],"TED-LIUM":[20],"corpus.":[21],"Data":[22],"augmentation":[23],"using":[24,39],"SpecAugment":[25,52],"is":[26,68],"successfully":[27],"applied":[28,69],"improve":[30],"performance":[31],"top":[33],"our":[35],"best":[36,88],"SAT":[37],"model":[38,59],"i-vectors.":[40],"By":[41],"investigating":[42],"effect":[44],"different":[46],"maskings,":[47],"we":[48],"achieve":[49],"improvements":[50],"from":[51],"HMM":[55],"models":[56,82],"without":[57],"increasing":[58],"size":[60],"and":[61,76,79,85],"time.":[63],"A":[64],"subsequent":[65],"sMBR":[66],"fine-tune":[71],"final":[73],"acoustic":[74],"model,":[75],"both":[77],"LSTM":[78],"Transformer":[80],"language":[81],"are":[83],"trained":[84],"evaluated.":[86],"Our":[87],"achieves":[90],"5.6%":[92],"WER":[93],"test":[96],"set,":[97],"which":[98],"outperforms":[99],"previous":[101],"by":[103],"27%":[104],"relative.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}