{"id":"https://openalex.org/W4402112178","doi":"https://doi.org/10.21437/interspeech.2024-1063","title":"Joint Speaker Features Learning for Audio-visual Multichannel Speech Separation and Recognition","display_name":"Joint Speaker Features Learning for Audio-visual Multichannel Speech Separation and Recognition","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112178","doi":"https://doi.org/10.21437/interspeech.2024-1063"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1063","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/A5042515126","display_name":"Guinan Li","orcid":"https://orcid.org/0000-0002-2206-0237"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guinan Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081269555","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0002-6834-0322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113020902","display_name":"Youjun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youjun Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengzhe Geng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026334377","display_name":"Shujie Hu","orcid":"https://orcid.org/0000-0002-8475-4912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujie Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356635","display_name":"Zhe Li","orcid":"https://orcid.org/0000-0002-0519-7434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075023049","display_name":"Zengrui Jin","orcid":"https://orcid.org/0000-0002-2637-7880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zengrui Jin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088539115","display_name":"Tianzi Wang","orcid":"https://orcid.org/0000-0001-9512-5647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianzi Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035857878","display_name":"Xurong Xie","orcid":"https://orcid.org/0000-0002-6714-6296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5042515126"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1546072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1925","last_page":"1929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9359999895095825,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9214000105857849,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7845535278320312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7718968987464905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7717181444168091},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6120381951332092},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5434257984161377},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.45180219411849976},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.431515634059906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4213620722293854},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2029227912425995},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09574618935585022},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08043310046195984}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7845535278320312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718968987464905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7717181444168091},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6120381951332092},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5434257984161377},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.45180219411849976},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.431515634059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4213620722293854},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2029227912425995},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09574618935585022},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08043310046195984},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-1063","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/114605","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/114605","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:bd04a596-9d27-4c63-a31a-7af7ad46aac1","is_oa":false,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=bd04a596-9d27-4c63-a31a-7af7ad46aac1","pdf_url":null,"source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"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":0,"referenced_works":[],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Interspeech":[0],"2024,":[1,4],"1-5":[2],"September":[3],"Kos,":[5],"Greece":[6]},"counts_by_year":[],"updated_date":"2026-03-02T08:37:19.008085","created_date":"2025-10-10T00:00:00"}
