{"id":"https://openalex.org/W7148546084","doi":"https://doi.org/10.1109/asru65441.2025.11434783","title":"ChipChat: Low-Latency Cascaded Conversational Agent in MLX","display_name":"ChipChat: Low-Latency Cascaded Conversational Agent in MLX","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148546084","doi":"https://doi.org/10.1109/asru65441.2025.11434783"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5106542588","display_name":"Tatiana Likhomanenko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tatiana Likhomanenko","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132817399","display_name":"Luke Carlson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luke Carlson","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104236780","display_name":"He Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard He Bai","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031982816","display_name":"Zijin Gu","orcid":"https://orcid.org/0000-0002-0385-2677"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zijin Gu","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132791982","display_name":"Han Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Han Tran","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090927958","display_name":"Zakaria Aldeneh","orcid":"https://orcid.org/0000-0003-4599-2448"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zakaria Aldeneh","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132804300","display_name":"Yizhe Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yizhe Zhang","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132808847","display_name":"Ruixiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruixiang Zhang","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132815487","display_name":"Huangjie Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huangjie Zheng","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112445699","display_name":"Navdeep Jaitly","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Navdeep Jaitly","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5106542588"],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8757608,"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":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.48179998993873596,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.48179998993873596,"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/T10028","display_name":"Topic Modeling","score":0.1005999967455864,"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/T12031","display_name":"Speech and dialogue systems","score":0.08100000023841858,"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/latency","display_name":"Latency (audio)","score":0.6489999890327454},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5575000047683716},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4973999857902527},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.45080000162124634},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.4212000072002411},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.40310001373291016},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36070001125335693},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.3513000011444092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299000263214111},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5575000047683716},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4973999857902527},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4632999897003174},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40880000591278076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40689998865127563},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27320000529289246},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5507276654243469,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W4389524500","https://openalex.org/W4393178509","https://openalex.org/W4408353632","https://openalex.org/W4411120495","https://openalex.org/W4412944968"],"related_works":[],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2],"large":[3],"language":[4,39],"models":[5],"(LLMs)":[6],"has":[7],"transformed":[8],"spoken":[9],"dialog":[10],"systems,":[11],"yet":[12],"the":[13],"optimal":[14],"architecture":[15],"for":[16,134],"real-time":[17],"on-device":[18,114],"voice":[19],"agents":[20],"remains":[21],"an":[22],"open":[23],"question.":[24],"While":[25],"end-to-end":[26],"approaches":[27],"promise":[28],"theoretical":[29],"advantages,":[30],"cascaded":[31],"systems":[32],"(CSs)":[33],"continue":[34],"to":[35],"outperform":[36],"them":[37],"in":[38],"understanding":[40],"tasks,":[41],"despite":[42],"being":[43],"constrained":[44],"by":[45],"sequential":[46],"processing":[47],"latency.":[48],"In":[49],"this":[50],"work,":[51],"we":[52],"introduce":[53],"ChipChat,":[54],"a":[55,102,130],"novel":[56],"low-latency":[57],"CS":[58],"that":[59,119],"overcomes":[60],"traditional":[61],"bottlenecks":[62],"through":[63,112],"architectural":[64],"innovations":[65],"and":[66,89],"streaming":[67,72],"optimizations.":[68],"Our":[69,116],"system":[70],"integrates":[71],"(a)":[73],"conversational":[74],"speech":[75],"recognition":[76],"with":[77],"mixture-of-experts,":[78],"(b)":[79],"state-action":[80],"augmented":[81],"LLM,":[82],"(c)":[83],"text-to-speech":[84],"synthesis,":[85],"(d)":[86],"neural":[87],"vocoder,":[88],"(e)":[90],"speaker":[91],"modeling.":[92],"Implemented":[93],"using":[94],"MLX,":[95],"ChipChat":[96],"achieves":[97],"subsecond":[98],"response":[99],"latency":[100,127],"on":[101],"Mac":[103],"Studio":[104],"without":[105],"dedicated":[106],"GPUs,":[107],"while":[108],"preserving":[109],"user":[110],"privacy":[111],"complete":[113],"processing.":[115],"work":[117],"shows":[118],"strategically":[120],"redesigned":[121],"CSs":[122],"can":[123],"overcome":[124],"their":[125],"historical":[126],"limitations,":[128],"offering":[129],"promising":[131],"path":[132],"forward":[133],"practical":[135],"voice-based":[136],"AI":[137],"agents.":[138]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}