{"id":"https://openalex.org/W4405709717","doi":"https://doi.org/10.1109/iscslp63861.2024.10800720","title":"A Dual-path Conformer-Based Network for Neural Speech Coding","display_name":"A Dual-path Conformer-Based Network for Neural Speech Coding","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709717","doi":"https://doi.org/10.1109/iscslp63861.2024.10800720"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800720","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":"conference-paper","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/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"],"raw_orcid":null,"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"],"raw_orcid":null,"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/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":false,"raw_author_name":"Yuhao Zhao","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology,Beijing"],"raw_orcid":null,"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":"https://openalex.org/A5101709936","display_name":"Liang Tao","orcid":"https://orcid.org/0000-0001-8553-8421"},"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":"Liang Tao","raw_affiliation_strings":["School of Information Science and Technology, Beijing University of Technology,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, Beijing University of Technology,Beijing","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"661","last_page":"665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9735999703407288,"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":0.9735999703407288,"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/T10320","display_name":"Neural Networks and Applications","score":0.9585999846458435,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.942300021648407,"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":0.6884338855743408},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5851328372955322},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5743544101715088},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5733320116996765},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5360090732574463},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.522476315498352},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5124590992927551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3641100227832794},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.28315553069114685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10210582613945007},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06709200143814087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6884338855743408},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5851328372955322},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5743544101715088},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5733320116996765},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5360090732574463},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.522476315498352},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5124590992927551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3641100227832794},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.28315553069114685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10210582613945007},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06709200143814087},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800720","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1728888090","https://openalex.org/W2593414223","https://openalex.org/W2775336875","https://openalex.org/W2935711438","https://openalex.org/W3015199127","https://openalex.org/W3015780049","https://openalex.org/W3096468295","https://openalex.org/W3097777922","https://openalex.org/W3100270690","https://openalex.org/W3120336970","https://openalex.org/W3160652646","https://openalex.org/W3161480375","https://openalex.org/W3163662330","https://openalex.org/W3169418678","https://openalex.org/W3215615641","https://openalex.org/W4225287045","https://openalex.org/W4307323391","https://openalex.org/W4372270198","https://openalex.org/W4375869380","https://openalex.org/W4377231659","https://openalex.org/W6629271464","https://openalex.org/W6630236247","https://openalex.org/W6638667902","https://openalex.org/W6640185926","https://openalex.org/W6760712927","https://openalex.org/W6783867762","https://openalex.org/W6802517614","https://openalex.org/W6852581948","https://openalex.org/W6853515095"],"related_works":["https://openalex.org/W2317351040","https://openalex.org/W2952466936","https://openalex.org/W1988622314","https://openalex.org/W2393949104","https://openalex.org/W4236344264","https://openalex.org/W1911859126","https://openalex.org/W2120730869","https://openalex.org/W1569721167","https://openalex.org/W2541680182","https://openalex.org/W2166699153"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,33,58],"neural":[6,96],"speech":[7,76],"coding":[8],"method":[9],"based":[10],"on":[11],"the":[12,22,27,37,40,51,72,90,94,100],"dual-path":[13,41],"conformer,":[14,42],"which":[15],"mainly":[16],"consists":[17],"of":[18,26,54,75,107],"three":[19],"steps:":[20],"(1)":[21],"encoding":[23],"and":[24,39,56,62,65,85,99],"decoding":[25],"time-frequency":[28],"spectrum":[29],"are":[30,68],"performed":[31],"by":[32],"structure":[34],"that":[35,89],"combines":[36],"CNN":[38],"(2)":[43],"residual":[44],"vector":[45],"quantization":[46],"is":[47],"employed":[48],"to":[49,70],"quantize":[50],"output":[52],"features":[53],"encoder":[55],"form":[57],"compact":[59],"discrete":[60],"representation,":[61],"(3)":[63],"multi-period":[64],"multi-scale":[66],"discriminators":[67],"used":[69],"improve":[71],"perceptual":[73],"quality":[74],"during":[77],"adversarial":[78],"training.":[79],"Experimental":[80],"results,":[81],"from":[82],"both":[83],"subjective":[84],"objective":[86],"evaluations,":[87],"demonstrate":[88],"proposed":[91],"codec":[92,97,103],"outperforms":[93],"state-of-the-art":[95],"AudioDEC":[98],"leading":[101],"conventional":[102],"Opus":[104],"in":[105],"terms":[106],"performance.":[108]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}