{"id":"https://openalex.org/W2972504708","doi":"https://doi.org/10.21437/interspeech.2019-2726","title":"Investigating the Lombard Effect Influence on End-to-End Audio-Visual Speech Recognition","display_name":"Investigating the Lombard Effect Influence on End-to-End Audio-Visual Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972504708","doi":"https://doi.org/10.21437/interspeech.2019-2726","mag":"2972504708"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2726","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7204,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85042681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7258021831512451},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7224639058113098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.672736644744873},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4983541965484619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18570205569267273},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18128782510757446}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7258021831512451},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7224639058113098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.672736644744873},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4983541965484619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18570205569267273},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18128782510757446}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2726","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3179968364","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2074916782","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731"],"abstract_inverted_index":{"Several":[0],"audio-visual":[1,75,179],"speech":[2,48,58,76,109,121,138],"recognition":[3],"models":[4,17],"have":[5],"been":[6],"recently":[7],"proposed":[8],"which":[9,44,89],"aim":[10],"to":[11,46,124],"improve":[12],"the":[13,19,29,32,36,54,60,68,71,79,86,125,129,149,154,172,178],"robustness":[14],"over":[15],"audio-only":[16,184],"in":[18,38,41,74,131,153],"presence":[20],"of":[21,26,31,57,70,81,119,171,183],"noise.":[22],"However,":[23],"almost":[24],"all":[25],"them":[27],"ignore":[28],"impact":[30,69],"Lombard":[33,72,108,120,137],"effect,":[34],"i.e.,":[35],"change":[37],"speaking":[39],"style":[40],"noisy":[42,136,164],"environments":[43],"aims":[45],"make":[47],"more":[49],"intelligible":[50],"and":[51,59,96,161,175,194],"affects":[52],"both":[53],"acoustic":[55],"characteristics":[56],"lip":[61],"movements.":[62],"In":[63,181],"this":[64,84],"paper,":[65],"we":[66],"investigate":[67],"effect":[73],"recognition.":[77],"To":[78],"best":[80],"our":[82],"knowledge,":[83],"is":[85,110,122,139,159,187],"first":[87],"work":[88],"does":[90],"so":[91],"using":[92],"end-to-end":[93],"deep":[94],"architectures":[95],"presents":[97],"results":[98,103],"on":[99,163],"unseen":[100],"speakers.":[101],"Our":[102],"show":[104,147],"that":[105,148],"properly":[106],"modelling":[107],"always":[111],"beneficial.":[112],"Even":[113],"if":[114],"a":[115,132,157,168],"relatively":[116],"small":[117],"amount":[118],"added":[123],"training":[126],"set":[127],"then":[128],"performance":[130,174,186],"real":[133],"scenario,":[134],"where":[135,156],"present,":[140],"can":[141],"be":[142],"significantly":[143],"improved.":[144],"We":[145],"also":[146],"standard":[150],"approach":[151],"followed":[152],"literature,":[155],"model":[158],"trained":[160],"tested":[162],"plain":[165],"speech,":[166],"provides":[167],"correct":[169],"estimate":[170],"video-only":[173],"slightly":[176],"underestimates":[177],"performance.":[180],"case":[182],"approaches,":[185],"overestimated":[188],"for":[189,196],"SNRs":[190],"higher":[191],"than":[192],"-3dB":[193],"underestimated":[195],"lower":[197],"SNRs.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}