{"id":"https://openalex.org/W4402112230","doi":"https://doi.org/10.21437/interspeech.2024-958","title":"Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement","display_name":"Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112230","doi":"https://doi.org/10.21437/interspeech.2024-958"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-958","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-958","pdf_url":"https://www.isca-archive.org/interspeech_2024/cheng24_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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/cheng24_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011611391","display_name":"Longbiao Cheng","orcid":"https://orcid.org/0000-0002-0635-1480"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longbiao Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050492887","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3352-7453"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051651857","display_name":"Tobi Delbr\u00fcck","orcid":"https://orcid.org/0000-0001-5479-1141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobi Delbruck","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053821067","display_name":"Shih\u2010Chii Liu","orcid":"https://orcid.org/0000-0002-7557-045X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shih-Chii Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.417,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9345215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"677","last_page":"681"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9915000200271606,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8570429086685181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7731086611747742},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5606546401977539},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49761489033699036},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4921409487724304},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4650263786315918},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44344061613082886},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4381554424762726},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.4140395224094391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36388087272644043},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3416796922683716},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27971550822257996},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18923181295394897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07433399558067322}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8570429086685181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731086611747742},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5606546401977539},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49761489033699036},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4921409487724304},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4650263786315918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44344061613082886},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4381554424762726},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.4140395224094391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36388087272644043},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3416796922683716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27971550822257996},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18923181295394897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07433399558067322},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-958","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-958","pdf_url":"https://www.isca-archive.org/interspeech_2024/cheng24_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"},{"id":"pmh:oai:arXiv.org:2408.12425","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.12425","pdf_url":"https://arxiv.org/pdf/2408.12425","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.5167/uzh-268735","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-958","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-958","pdf_url":"https://www.isca-archive.org/interspeech_2024/cheng24_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":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112230.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W2022544890","https://openalex.org/W2394097730","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273"],"abstract_inverted_index":{"This":[0,55],"paper":[1],"introduces":[2],"a":[3,36,46,73],"new":[4],"Dynamic":[5,82],"Gated":[6,83],"Recurrent":[7,84],"Neural":[8],"Network":[9],"(DG-RNN)":[10],"for":[11],"compute-efficient":[12,99],"speech":[13,101,118],"enhancement":[14,102],"models":[15,129],"running":[16],"on":[17],"resource-constrained":[18],"hardware":[19],"platforms.":[20],"It":[21],"leverages":[22],"the":[23,52,59,63,76,81,105,111,125],"slow":[24],"evolution":[25],"characteristic":[26],"of":[27,39,62,75],"RNN":[28,53,65],"hidden":[29],"states":[30],"over":[31],"steps,":[32],"and":[33,120],"updates":[34],"only":[35],"selected":[37],"set":[38],"neurons":[40],"at":[41],"each":[42],"step":[43],"by":[44],"adding":[45],"newly":[47],"proposed":[48],"select":[49,56],"gate":[50,57],"to":[51,66,124],"model.":[54],"allows":[58],"computation":[60],"cost":[61],"conventional":[64],"be":[67],"reduced":[68],"during":[69],"network":[70],"inference.":[71],"As":[72],"realization":[74],"DG-RNN,":[77],"we":[78],"further":[79],"propose":[80],"Unit":[85],"(D-GRU)":[86],"which":[87],"does":[88],"not":[89],"require":[90],"additional":[91],"parameters.":[92],"Test":[93],"results":[94],"obtained":[95],"from":[96],"several":[97],"state-of-the-art":[98],"RNN-based":[100],"architectures":[103],"using":[104],"DNS":[106],"challenge":[107],"dataset,":[108],"show":[109],"that":[110],"D-GRU":[112],"based":[113,128],"model":[114],"variants":[115],"maintain":[116],"similar":[117],"intelligibility":[119],"quality":[121],"metrics":[122],"comparable":[123],"baseline":[126],"GRU":[127,137],"even":[130],"with":[131],"an":[132],"average":[133],"50%":[134],"reduction":[135],"in":[136],"computes.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}