{"id":"https://openalex.org/W4385822542","doi":"https://doi.org/10.21437/interspeech.2023-487","title":"Streaming Audio-Visual Speech Recognition with Alignment Regularization","display_name":"Streaming Audio-Visual Speech Recognition with Alignment Regularization","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822542","doi":"https://doi.org/10.21437/interspeech.2023-487"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-487","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5101728918","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0001-7680-2817"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013781881","display_name":"Niko Moritz","orcid":"https://orcid.org/0000-0003-4352-8115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niko Moritz","raw_affiliation_strings":[],"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":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047073253","display_name":"Christian Fuegen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Fuegen","raw_affiliation_strings":[],"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":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101728918"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4066,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56506228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1598","last_page":"1602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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":0.9966999888420105,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9606000185012817,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9549000263214111,"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/computer-science","display_name":"Computer science","score":0.7928452491760254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7457006573677063},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6801052093505859},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5942401885986328},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5262029767036438},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.474514901638031},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4263703525066376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4103821814060211},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3829346001148224},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.27853769063949585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928452491760254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7457006573677063},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6801052093505859},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5942401885986328},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5262029767036438},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.474514901638031},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4263703525066376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4103821814060211},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3829346001148224},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.27853769063949585}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-487","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1546240199","https://openalex.org/W2069501481","https://openalex.org/W2157598242","https://openalex.org/W2063862874","https://openalex.org/W46679383","https://openalex.org/W1911859126","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}