{"id":"https://openalex.org/W4405709311","doi":"https://doi.org/10.1109/iscslp63861.2024.10800201","title":"A Hybrid DFSMN and Mamba Architecture for Low Bitrate Neural Speech Coding","display_name":"A Hybrid DFSMN and Mamba Architecture for Low Bitrate Neural Speech Coding","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709311","doi":"https://doi.org/10.1109/iscslp63861.2024.10800201"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100586810","display_name":"Yuhao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhao Zhao","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology,Beijing","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000601742","display_name":"Maoshen Jia","orcid":"https://orcid.org/0000-0002-3452-3913"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoshen Jia","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology,Beijing","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023530820","display_name":"Jiawei Ru","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Ru","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology,Beijing","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":null,"display_name":"Junqi Tai","orcid":null},"institutions":[{"id":"https://openalex.org/I316699675","display_name":"Hodges University","ror":"https://ror.org/00s8h5d08","country_code":"US","type":"education","lineage":["https://openalex.org/I316699675"]},{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Junqi Tai","raw_affiliation_strings":["Beijing-Dublin International College, Beijing University of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"Beijing-Dublin International College, Beijing University of Technology,Beijing","institution_ids":["https://openalex.org/I316699675","https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100586810"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25778767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9955999851226807,"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":0.9955999851226807,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9948999881744385,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9944000244140625,"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":0.7131562232971191},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5737005472183228},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5572705864906311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48334071040153503},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09497752785682678},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07072600722312927},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.04247727990150452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131562232971191},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5737005472183228},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5572705864906311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48334071040153503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09497752785682678},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07072600722312927},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.04247727990150452},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G310012415","display_name":null,"funder_award_id":"L233032,L223033","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G852593933","display_name":null,"funder_award_id":"62471012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2147800946","https://openalex.org/W2151626637","https://openalex.org/W2208299922","https://openalex.org/W2289400088","https://openalex.org/W2396073756","https://openalex.org/W2775336875","https://openalex.org/W2963208781","https://openalex.org/W2963308316","https://openalex.org/W3015338123","https://openalex.org/W3037038648","https://openalex.org/W3092028330","https://openalex.org/W3120336970","https://openalex.org/W3163662330","https://openalex.org/W3209374680","https://openalex.org/W3215615641","https://openalex.org/W4225287045","https://openalex.org/W4307323391","https://openalex.org/W4372270198","https://openalex.org/W4372279529","https://openalex.org/W4375869380","https://openalex.org/W4385245566","https://openalex.org/W4389326242","https://openalex.org/W4391013663","https://openalex.org/W4393943345"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,34],"this":[1],"paper,":[2],"we":[3],"proposed":[4,18,36,102],"a":[5,22,27,31,38],"novel":[6],"low":[7,95],"bitrate":[8],"neural":[9],"speech":[10,88],"codec":[11,82],"based":[12],"on":[13],"sequence":[14],"modeling":[15],"networks.":[16],"The":[17],"method":[19,103],"consists":[20],"of":[21,87],"convolution-based":[23],"encoder":[24],"and":[25,30,70,113],"decoder,":[26],"DFSMN-Mamba":[28,39],"module,":[29],"vector":[32],"quantizer.":[33],"the":[35,62,80,101,108],"method,":[37],"module":[40],"is":[41,58,76],"designed":[42],"by":[43],"combining":[44],"Deep":[45],"Feedforward":[46],"Sequential":[47],"Memory":[48],"Network":[49],"(DFSMN)":[50],"with":[51],"selective":[52],"state":[53],"space":[54],"model":[55,61],"Mamba,":[56],"which":[57,84],"used":[59,77],"to":[60,78],"input":[63],"features":[64],"in":[65,67,110],"parallel":[66],"both":[68,111],"time":[69],"frequency":[71],"dimensions.":[72],"An":[73],"adversarial":[74],"loss":[75],"train":[79],"entire":[81],"framework,":[83],"enables":[85],"compression":[86],"waveforms":[89],"into":[90],"compact":[91],"discrete":[92],"representations":[93],"at":[94],"bitrates.":[96],"Experimental":[97],"results":[98],"show":[99],"that":[100],"achieves":[104],"better":[105],"performance":[106],"than":[107],"baseline":[109],"subjective":[112],"objective":[114],"evaluation.":[115]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}