{"id":"https://openalex.org/W4402112006","doi":"https://doi.org/10.21437/interspeech.2024-745","title":"Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval","display_name":"Cross-Modal Denoising: A Novel Training Paradigm for Enhancing Speech-Image Retrieval","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112006","doi":"https://doi.org/10.21437/interspeech.2024-745"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-745","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-745","pdf_url":"https://www.isca-archive.org/interspeech_2024/zhou24c_interspeech.pdf","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":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/zhou24c_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041045546","display_name":"Lifeng Zhou","orcid":"https://orcid.org/0000-0001-7927-8504"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifeng Zhou","raw_affiliation_strings":["Netease Yidun AI Lab , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease Yidun AI Lab , Hangzhou , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697197","display_name":"Yuke Li","orcid":"https://orcid.org/0000-0002-5242-9066"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["Netease Yidun AI Lab , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease Yidun AI Lab , Hangzhou , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101655486","display_name":"Rui Deng","orcid":"https://orcid.org/0000-0002-6511-8662"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Deng","raw_affiliation_strings":["Netease Yidun AI Lab , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease Yidun AI Lab , Hangzhou , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101847696","display_name":"Yuting Yang","orcid":"https://orcid.org/0000-0003-1205-2329"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Yang","raw_affiliation_strings":["Netease Yidun AI Lab , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease Yidun AI Lab , Hangzhou , China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012539121","display_name":"Haoqi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqi Zhu","raw_affiliation_strings":["Netease Yidun AI Lab , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netease Yidun AI Lab , Hangzhou , China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":0.5972,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73345424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4064","last_page":"4068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8614000082015991,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8614000082015991,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8574000000953674,"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":0.8147000074386597,"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":0.7677476406097412},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6278393268585205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6014785766601562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.564812183380127},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5244194269180298},{"id":"https://openalex.org/keywords/image-denoising","display_name":"Image denoising","score":0.43359941244125366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40214699506759644},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3434292674064636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677476406097412},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6278393268585205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6014785766601562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.564812183380127},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5244194269180298},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.43359941244125366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40214699506759644},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3434292674064636},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-745","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-745","pdf_url":"https://www.isca-archive.org/interspeech_2024/zhou24c_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-745","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-745","pdf_url":"https://www.isca-archive.org/interspeech_2024/zhou24c_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112006.pdf","grobid_xml":"https://content.openalex.org/works/W4402112006.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2895947835","https://openalex.org/W2087258800","https://openalex.org/W2810018092","https://openalex.org/W2387428419","https://openalex.org/W4401571043","https://openalex.org/W2098237619","https://openalex.org/W1974034585","https://openalex.org/W2353444452","https://openalex.org/W2001438600","https://openalex.org/W2499707420"],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2,24,28,147],"speech-image":[3,136],"retrieval":[4,137],"relies":[5],"on":[6,120,130],"establishing":[7],"an":[8,45],"effective":[9,46],"alignment":[10],"between":[11],"speech":[12],"and":[13,48,94,124,145],"image.Existing":[14],"methods":[15],"often":[16],"model":[17,92],"cross-modal":[18,54,59,64],"interaction":[19,60],"through":[20],"simple":[21],"cosine":[22],"similarity":[23],"the":[25,112,121,131,135,143],"global":[26],"feature":[27],"each":[29],"modality,":[30],"which":[31],"fall":[32],"short":[33],"in":[34,117,127],"capturing":[35],"fine-grained":[36],"details":[37],"within":[38,79],"modalities.To":[39],"address":[40],"this":[41],"issue,":[42],"we":[43],"introduce":[44],"framework":[47,110],"a":[49,68],"novel":[50],"learning":[51],"task":[52,70],"named":[53],"denoising":[55,69],"(CMD)":[56],"to":[57,61,72],"enhance":[58],"achieve":[62],"finerlevel":[63],"alignment.Specifically,":[65],"CMD":[66,88],"is":[67],"designed":[71],"reconstruct":[73],"semantic":[74],"features":[75,78,84],"from":[76,85],"noisy":[77],"one":[80],"modality":[81],"by":[82,115,125],"interacting":[83],"another":[86],"modality.Notably,":[87],"operates":[89],"exclusively":[90],"during":[91,98],"training":[93],"can":[95],"be":[96],"removed":[97],"inference":[99,103],"without":[100],"adding":[101],"extra":[102],"time.The":[104],"experimental":[105,140],"results":[106,141],"demonstrate":[107],"that":[108],"our":[109,148],"outperforms":[111],"state-of-the-art":[113],"method":[114],"2.0%":[116],"mean":[118,128],"R@1":[119,129],"Flickr8k":[122],"dataset":[123,133],"1.7%":[126],"SpokenCOCO":[132],"for":[134],"tasks,":[138],"respectively.These":[139],"validate":[142],"efficiency":[144],"effectiveness":[146],"framework.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}