{"id":"https://openalex.org/W1969975883","doi":"https://doi.org/10.1109/icassp.2013.6638354","title":"Twin-HMM-based audio-visual speech enhancement","display_name":"Twin-HMM-based audio-visual speech enhancement","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W1969975883","doi":"https://doi.org/10.1109/icassp.2013.6638354","mag":"1969975883"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5101807751","display_name":"Ahmed Hussen Abdelaziz","orcid":"https://orcid.org/0000-0001-8027-4666"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ahmed Hussen Abdelaziz","raw_affiliation_strings":["Insititute of Communication Acoustics, Digital Signal Processing Group, Ruhr Universit\u00e4t Bochum, Bochum, Germany","Digital Signal Process. Group, Ruhr-Univ. Bochum, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Insititute of Communication Acoustics, Digital Signal Processing Group, Ruhr Universit\u00e4t Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]},{"raw_affiliation_string":"Digital Signal Process. Group, Ruhr-Univ. Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046724251","display_name":"Steffen Zeiler","orcid":"https://orcid.org/0009-0002-9594-2633"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Zeiler","raw_affiliation_strings":["Insititute of Communication Acoustics, Digital Signal Processing Group, Ruhr Universit\u00e4t Bochum, Bochum, Germany","Digital Signal Process. Group, Ruhr-Univ. Bochum, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Insititute of Communication Acoustics, Digital Signal Processing Group, Ruhr Universit\u00e4t Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]},{"raw_affiliation_string":"Digital Signal Process. Group, Ruhr-Univ. Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007017640","display_name":"Dorothea Kolossa","orcid":"https://orcid.org/0000-0003-0678-3053"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorothea Kolossa","raw_affiliation_strings":["Insititute of Communication Acoustics, Digital Signal Processing Group, Ruhr Universit\u00e4t Bochum, Bochum, Germany","Digital Signal Process. Group, Ruhr-Univ. Bochum, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Insititute of Communication Acoustics, Digital Signal Processing Group, Ruhr Universit\u00e4t Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]},{"raw_affiliation_string":"Digital Signal Process. Group, Ruhr-Univ. Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101807751"],"corresponding_institution_ids":["https://openalex.org/I904495901"],"apc_list":null,"apc_paid":null,"fwci":2.5537,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.894108,"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":"3726","last_page":"3730"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8475053906440735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912856340408325},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7836997509002686},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6590818762779236},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5450811386108398},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5333666205406189},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.47615504264831543},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4567784368991852},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4544757008552551},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4232894778251648},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4221823811531067},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4186713695526123},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4134792387485504},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3769720494747162},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.36348360776901245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34176763892173767},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.26377642154693604},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20833522081375122},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12000453472137451},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11775439977645874},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10572710633277893},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08884871006011963},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07774537801742554}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8475053906440735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912856340408325},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7836997509002686},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6590818762779236},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5450811386108398},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5333666205406189},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.47615504264831543},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4567784368991852},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4544757008552551},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4232894778251648},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4221823811531067},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4186713695526123},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4134792387485504},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3769720494747162},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.36348360776901245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34176763892173767},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.26377642154693604},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20833522081375122},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12000453472137451},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11775439977645874},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10572710633277893},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08884871006011963},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07774537801742554},{"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/icassp.2013.6638354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W31621703","https://openalex.org/W266272917","https://openalex.org/W306230967","https://openalex.org/W1546892833","https://openalex.org/W1552314771","https://openalex.org/W1610379133","https://openalex.org/W1974192711","https://openalex.org/W1978380426","https://openalex.org/W2015143272","https://openalex.org/W2016254085","https://openalex.org/W2067295501","https://openalex.org/W2125838338","https://openalex.org/W2137400100","https://openalex.org/W2138425792","https://openalex.org/W2146324387","https://openalex.org/W2148154194","https://openalex.org/W2406453083","https://openalex.org/W2406954482","https://openalex.org/W3143833948","https://openalex.org/W4245919820","https://openalex.org/W6601288365","https://openalex.org/W6609921303","https://openalex.org/W6667372801","https://openalex.org/W6713510121"],"related_works":["https://openalex.org/W3211091508","https://openalex.org/W2289868279","https://openalex.org/W72660888","https://openalex.org/W2384738070","https://openalex.org/W2735200146","https://openalex.org/W2109142991","https://openalex.org/W1590604789","https://openalex.org/W2792033502","https://openalex.org/W2065633372","https://openalex.org/W3043119899"],"abstract_inverted_index":{"Most":[0],"approaches":[1],"for":[2,63,82],"speech":[3,64,96],"signal":[4],"processing":[5,65],"rely":[6],"solely":[7],"on":[8,92],"acoustic":[9],"input,":[10],"which":[11],"has":[12],"the":[13,22,50,73,87],"consequence":[14],"that":[15],"spectrum":[16],"estimation":[17],"becomes":[18],"exceedingly":[19],"difficult":[20],"when":[21],"signal-to-noise":[23],"ratio":[24],"drops":[25],"to":[26,55],"values":[27],"near":[28],"0":[29],"dB.":[30],"However,":[31],"alternative":[32],"sources":[33],"of":[34,43],"information":[35],"are":[36],"becoming":[37],"widely":[38],"available":[39],"with":[40],"increasing":[41],"use":[42,56],"multimedia":[44],"data":[45,84],"in":[46],"everyday":[47],"communication.":[48],"In":[49],"following":[51],"paper,":[52],"we":[53],"suggest":[54],"video":[57],"input":[58],"as":[59],"an":[60],"auxiliary":[61],"modality":[62],"by":[66],"applying":[67],"a":[68],"new":[69],"statistical":[70],"model":[71],"-":[72],"twin":[74],"hidden":[75],"Markov":[76],"model.":[77],"The":[78],"resulting":[79],"enhancement":[80],"algorithm":[81],"audiovisual":[83],"greatly":[85],"outperforms":[86],"standard":[88],"audio-only":[89],"log-MMSE":[90],"estimator":[91],"all":[93],"considered":[94],"instrumental":[95],"quality":[97],"measures":[98],"covering":[99],"spectral":[100],"and":[101],"perceptual":[102],"quality.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}