{"id":"https://openalex.org/W4402111990","doi":"https://doi.org/10.21437/interspeech.2024-703","title":"One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model","display_name":"One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111990","doi":"https://doi.org/10.21437/interspeech.2024-703"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-703","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-703","pdf_url":null,"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":"green","oa_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=a290e7ac-4bb1-406d-9936-a996cb5b4729","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101675941","display_name":"Zhaoqing Li","orcid":"https://orcid.org/0000-0001-8649-4934"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhaoqing Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063907750","display_name":"Haoning Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoning Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407750","display_name":"Tianzi Wang","orcid":"https://orcid.org/0009-0005-5823-3039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianzi Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045355404","display_name":"Shoukang Hu","orcid":"https://orcid.org/0000-0002-3345-6923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shoukang Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075023049","display_name":"Zengrui Jin","orcid":"https://orcid.org/0000-0002-2637-7880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zengrui Jin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026334377","display_name":"Shujie Hu","orcid":"https://orcid.org/0000-0002-8475-4912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujie Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081269555","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0002-6834-0322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065896539","display_name":"Mingyu Cui","orcid":"https://orcid.org/0000-0001-9781-9407"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyu Cui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengzhe Geng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5101675941"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3636,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66454149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4503","last_page":"4507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8647000193595886,"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/T10320","display_name":"Neural Networks and Applications","score":0.8647000193595886,"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":0.7883999943733215,"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/T10860","display_name":"Speech and Audio Processing","score":0.729200005531311,"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/quantization","display_name":"Quantization (signal processing)","score":0.6557927131652832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5562983751296997},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4721924066543579},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4416346848011017},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4386041462421417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4154224097728729},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2413070797920227}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6557927131652832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5562983751296997},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4721924066543579},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4416346848011017},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4386041462421417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4154224097728729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2413070797920227},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-703","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-703","pdf_url":null,"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:cisti-icist.nrc-cnrc.ca:cistinparc:a290e7ac-4bb1-406d-9936-a996cb5b4729","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=a290e7ac-4bb1-406d-9936-a996cb5b4729","pdf_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=a290e7ac-4bb1-406d-9936-a996cb5b4729","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:a290e7ac-4bb1-406d-9936-a996cb5b4729","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=a290e7ac-4bb1-406d-9936-a996cb5b4729","pdf_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=a290e7ac-4bb1-406d-9936-a996cb5b4729","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111990.pdf","grobid_xml":"https://content.openalex.org/works/W4402111990.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W2220552745","https://openalex.org/W2777605427"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,59,64],"novel":[3],"one-pass":[4],"multiple":[5,23,54],"ASR":[6,55],"systems":[7,25,48,56,83],"joint":[8],"compression":[9,20,91,101],"and":[10,31,44,92,105,114],"quantization":[11,32],"approach":[12],"using":[13],"an":[14],"all-in-one":[15,61],"neural":[16],"model.":[17],"A":[18,87],"single":[19,60],"cycle":[21],"allows":[22],"nested":[24],"with":[26],"varying":[27],"Encoder":[28],"depths,":[29],"widths,":[30],"precision":[33],"settings":[34],"to":[35,42,75],"be":[36],"simultaneously":[37],"constructed":[38],"without":[39],"the":[40,53,110],"need":[41],"train":[43],"store":[45],"individual":[46],"target":[47],"separately.":[49],"Experiments":[50],"consistently":[51],"demonstrate":[52],"compressed":[57],"in":[58],"model":[62,99],"produced":[63],"word":[65],"error":[66],"rate":[67],"(WER)":[68],"comparable":[69],"to,":[70],"or":[71],"lower":[72],"by":[73],"up":[74],"1.01%":[76],"absolute":[77],"(6.98%":[78],"relative)":[79],"than":[80],"individually":[81],"trained":[82],"of":[84,103],"equal":[85],"complexity.":[86],"3.4x":[88],"overall":[89],"system":[90],"training":[93],"time":[94],"speed-up":[95],"was":[96],"achieved.":[97],"Maximum":[98],"size":[100],"ratios":[102],"12.8x":[104],"3.93x":[106],"were":[107],"obtained":[108],"over":[109],"baseline":[111],"Switchboard-300hr":[112],"Conformer":[113],"LibriSpeech-100hr":[115],"fine-tuned":[116],"wav2vec2.0":[117],"models,":[118],"respectively,":[119],"incurring":[120],"no":[121],"statistically":[122],"significant":[123],"WER":[124],"increase.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}