{"id":"https://openalex.org/W2406846463","doi":"https://doi.org/10.21437/interspeech.2015-204","title":"Integration of deep bottleneck features for audio-visual speech recognition","display_name":"Integration of deep bottleneck features for audio-visual speech recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2406846463","doi":"https://doi.org/10.21437/interspeech.2015-204","mag":"2406846463"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-204","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5101639573","display_name":"Hiroshi Ninomiya","orcid":"https://orcid.org/0000-0003-3418-3178"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hiroshi Ninomiya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077234015","display_name":"Norihide Kitaoka","orcid":"https://orcid.org/0000-0003-2028-8585"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Norihide Kitaoka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808735","display_name":"Satoshi Tamura","orcid":"https://orcid.org/0000-0001-6916-4618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Tamura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112017946","display_name":"Yurie Iribe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yurie Iribe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101639573"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8822,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95930504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"563","last_page":"567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.7679725885391235},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7577651143074036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7025940418243408},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6384122371673584},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.20867407321929932},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.09575334191322327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7679725885391235},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7577651143074036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7025940418243408},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6384122371673584},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20867407321929932},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09575334191322327}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-204","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1970088388","https://openalex.org/W2022799064","https://openalex.org/W2076462394","https://openalex.org/W2100495367","https://openalex.org/W2112796928","https://openalex.org/W2184045248","https://openalex.org/W2184188583","https://openalex.org/W2394932179","https://openalex.org/W2395273492","https://openalex.org/W2397904770"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}