{"id":"https://openalex.org/W4405015015","doi":"https://doi.org/10.1145/3636534.3697460","title":"TraMSR: Transformer and Mamba based Practical Speech Super-Resolution for Mobile Wearables","display_name":"TraMSR: Transformer and Mamba based Practical Speech Super-Resolution for Mobile Wearables","publication_year":2024,"publication_date":"2024-12-04","ids":{"openalex":"https://openalex.org/W4405015015","doi":"https://doi.org/10.1145/3636534.3697460"},"language":"en","primary_location":{"id":"doi:10.1145/3636534.3697460","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3636534.3697460","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3636534.3697460","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Annual International Conference on Mobile Computing and Networking","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3636534.3697460","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101443153","display_name":"Yueyuan Sui","orcid":"https://orcid.org/0009-0007-1602-5359"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yueyuan Sui","raw_affiliation_strings":["Northwestern University, Evanston, United States"],"raw_orcid":"https://orcid.org/0009-0007-1602-5359","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, United States","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012350268","display_name":"Minghui Zhao","orcid":"https://orcid.org/0000-0003-1999-0078"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minghui Zhao","raw_affiliation_strings":["Columbia University, New York, United States"],"raw_orcid":"https://orcid.org/0000-0003-1999-0078","affiliations":[{"raw_affiliation_string":"Columbia University, New York, United States","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102703573","display_name":"Junxi Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junxi Xia","raw_affiliation_strings":["Northwestern University, Evanston, USA"],"raw_orcid":"https://orcid.org/0009-0005-7356-1348","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063824268","display_name":"Xiaofan Jiang","orcid":"https://orcid.org/0000-0002-6480-0299"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofan Jiang","raw_affiliation_strings":["Columbia University, New York, United States"],"raw_orcid":"https://orcid.org/0000-0002-6480-0299","affiliations":[{"raw_affiliation_string":"Columbia University, New York, United States","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051730108","display_name":"Stephen Xia","orcid":"https://orcid.org/0000-0001-5713-8885"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Xia","raw_affiliation_strings":["Northwestern University, Evanston, United States"],"raw_orcid":"https://orcid.org/0000-0001-5713-8885","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, United States","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1686","last_page":"1688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9958000183105469,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9879999756813049,"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/computer-science","display_name":"Computer science","score":0.7062646150588989},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.6867626309394836},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6222351789474487},{"id":"https://openalex.org/keywords/smartwatch","display_name":"Smartwatch","score":0.5031659007072449},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4753955602645874},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3333442509174347},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.24727174639701843},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.22949188947677612},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16404950618743896},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09056150913238525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062646150588989},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.6867626309394836},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6222351789474487},{"id":"https://openalex.org/C29794715","wikidata":"https://www.wikidata.org/wiki/Q5362345","display_name":"Smartwatch","level":3,"score":0.5031659007072449},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4753955602645874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3333442509174347},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.24727174639701843},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.22949188947677612},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16404950618743896},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09056150913238525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3636534.3697460","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3636534.3697460","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3636534.3697460","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Annual International Conference on Mobile Computing and Networking","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3636534.3697460","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3636534.3697460","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3636534.3697460","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Annual International Conference on Mobile Computing and Networking","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405015015.pdf"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2476548250","https://openalex.org/W2760103357","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3211264909","https://openalex.org/W3213952100","https://openalex.org/W4200628964","https://openalex.org/W4372260387"],"related_works":["https://openalex.org/W4285587629","https://openalex.org/W2756171776","https://openalex.org/W2765158217","https://openalex.org/W2762811937","https://openalex.org/W2757470104","https://openalex.org/W3123444836","https://openalex.org/W2000367546","https://openalex.org/W4387817412","https://openalex.org/W2012157391","https://openalex.org/W2585232498"],"abstract_inverted_index":{"Speech":[0,87],"super-resolution":[1],"techniques":[2],"offer":[3],"a":[4,48],"promising":[5],"solution":[6],"to":[7,71,81,107],"enhance":[8],"audio":[9],"quality":[10],"in":[11,83,92],"wearable":[12],"devices,":[13],"particularly":[14],"when":[15],"addressing":[16],"the":[17],"challenges":[18],"of":[19,86,100],"reduced":[20],"sampling":[21],"rates":[22],"necessitated":[23],"by":[24,79],"battery":[25],"life":[26],"constraints":[27],"and":[28,54,90,105],"network":[29],"instability.":[30],"However,":[31],"existing":[32],"methods":[33],"either":[34],"prove":[35],"computationally":[36],"prohibitive":[37],"for":[38,57],"mobile":[39],"platforms,":[40],"or":[41],"lack":[42],"sufficient":[43],"performance.":[44],"We":[45],"present":[46],"TraMSR,":[47],"novel":[49],"hybrid":[50],"model":[51,75],"combining":[52],"transformer":[53],"Mamba":[55],"architectures":[56],"acoustic":[58],"speech":[59],"super-resolution.":[60],"TraMSR":[61],"achieves":[62],"superior":[63],"performance":[64],"while":[65],"significantly":[66],"reducing":[67],"computational":[68],"demands":[69],"compared":[70],"state-of-the-art":[72],"methods.":[73],"Our":[74],"outperforms":[76],"GAN-based":[77],"approaches":[78],"up":[80,106],"7.3%":[82],"Perceptual":[84],"Evaluation":[85],"Quality":[88],"(PESQ)":[89],"1.8%":[91],"Short-Time":[93],"Objective":[94],"Intelligibility":[95],"(STOI),":[96],"with":[97],"an":[98],"order":[99],"magnitude":[101],"smaller":[102],"memory":[103],"footprint":[104],"465":[108],"times":[109],"faster":[110],"inference":[111],"speed.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}