{"id":"https://openalex.org/W3095996511","doi":"https://doi.org/10.21437/interspeech.2020-1194","title":"Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer","display_name":"Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095996511","doi":"https://doi.org/10.21437/interspeech.2020-1194","mag":"3095996511"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5047358828","display_name":"Yuan Shangguan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Shangguan","raw_affiliation_strings":["Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010688440","display_name":"Kate Knister","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kate Knister","raw_affiliation_strings":["Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":["Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048236120","display_name":"Ian McGraw","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian McGraw","raw_affiliation_strings":["Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110711540","display_name":"Fran\u00e7oise Beaufays","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fran\u00e7oise Beaufays","raw_affiliation_strings":["Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC, 1600 Amphitheatre Parkway, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"591","last_page":"595"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9922999739646912,"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/T11309","display_name":"Music and Audio Processing","score":0.9812999963760376,"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/computer-science","display_name":"Computer science","score":0.8249709606170654},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7955518364906311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6703307628631592},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.62796950340271},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.49603304266929626},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4652577042579651},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4216774106025696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39353615045547485},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17383182048797607},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06070330739021301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249709606170654},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7955518364906311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6703307628631592},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.62796950340271},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.49603304266929626},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4652577042579651},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4216774106025696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39353615045547485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17383182048797607},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06070330739021301},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1991646969","https://openalex.org/W2119631826","https://openalex.org/W2121879602","https://openalex.org/W2163721076","https://openalex.org/W2394671344","https://openalex.org/W2515744007","https://openalex.org/W2805275761","https://openalex.org/W2962760690","https://openalex.org/W2963122170","https://openalex.org/W2963414781","https://openalex.org/W2975044525","https://openalex.org/W3008181812","https://openalex.org/W3015194534","https://openalex.org/W3015583403"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"The":[0],"demand":[1],"for":[2],"fast":[3],"and":[4,49,71,96],"accurate":[5],"incremental":[6],"speech":[7,15,19],"recognition":[8,16],"increases":[9],"as":[10],"the":[11,28,38,47,67,75,92],"applications":[12],"of":[13,23,51,63,77,94],"automatic":[14],"(ASR)":[17],"proliferate.Incremental":[18],"recognizers":[20],"output":[21],"chunks":[22],"partially":[24],"recognized":[25],"words":[26],"while":[27],"user":[29],"is":[30],"still":[31],"talking.Partial":[32],"results":[33],"can":[34],"be":[35],"revised":[36],"before":[37],"ASR":[39,56,107],"finalizes":[40],"its":[41],"hypothesis,":[42],"causing":[43],"instability":[44,68,95],"issues.We":[45],"analyze":[46],"quality":[48],"stability":[50],"on-device":[52],"streaming":[53,105],"end-to-end":[54],"(E2E)":[55],"models.We":[57],"first":[58],"introduce":[59],"a":[60,104],"novel":[61],"set":[62],"metrics":[64],"that":[65,82],"quantify":[66],"at":[69],"word":[70],"segment":[72],"levels.We":[73],"study":[74],"impact":[76],"several":[78],"model":[79,85,89],"training":[80],"techniques":[81],"improve":[83],"E2E":[84,106],"qualities":[86],"but":[87],"degrade":[88],"stability.We":[90],"categorize":[91],"causes":[93],"explore":[97],"various":[98],"solutions":[99],"to":[100],"mitigate":[101],"them":[102],"in":[103],"system.":[108]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}