{"id":"https://openalex.org/W4407953196","doi":"https://doi.org/10.1145/3701551.3706130","title":"Advancing Voice AI for E-commerce: Tracking ASR Model Performance at Scale","display_name":"Advancing Voice AI for E-commerce: Tracking ASR Model Performance at Scale","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4407953196","doi":"https://doi.org/10.1145/3701551.3706130"},"language":"en","primary_location":{"id":"doi:10.1145/3701551.3706130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701551.3706130","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701551.3706130?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701551.3706130?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072015638","display_name":"Dhruv Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dhruv Agarwal","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038578069","display_name":"Nupur K. Neti","orcid":"https://orcid.org/0000-0002-9272-3657"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nupur Neti","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047282567","display_name":"Federica Cerina","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Federica Cerina","raw_affiliation_strings":["Amazon, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072015638"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02992867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1084","last_page":"1085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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":0.9959999918937683,"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":0.7447683811187744},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5358520746231079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49840545654296875},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4257619082927704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447683811187744},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5358520746231079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49840545654296875},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4257619082927704},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701551.3706130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701551.3706130","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701551.3706130?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701551.3706130","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701551.3706130","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701551.3706130?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407953196.pdf"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4246270042","https://openalex.org/W4372260337"],"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":{"Traditionally,":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"systems":[5],"rely":[6],"on":[7],"human":[8,72],"transcriptions":[9],"to":[10,20,35,59],"calculate":[11],"word":[12],"error":[13],"rate":[14],"(WER)":[15],"by":[16],"comparing":[17],"ASR":[18,61,92],"outputs":[19],"manual":[21],"transcriptions.":[22],"Recently,":[23],"Amazon's":[24],"mobile":[25],"voice":[26,101],"shopping":[27],"platform":[28],"stopped":[29],"storing":[30,68],"audio":[31,69,84],"from":[32],"incoming":[33],"requests":[34],"enhance":[36],"customer":[37,100],"privacy,":[38],"making":[39],"offline,":[40],"human-based":[41],"evaluation":[42],"unfeasible.":[43],"This":[44],"presentation":[45],"introduces":[46],"a":[47,82],"multitask":[48],"Speech":[49],"LLM-based":[50],"system":[51],"that":[52],"processes":[53],"real-time":[54],"audio,":[55],"extracting":[56],"key":[57],"features":[58,80],"track":[60],"performance":[62,93],"and":[63],"detect":[64],"traffic":[65],"shifts-all":[66],"without":[67],"or":[70],"requiring":[71],"annotations.":[73],"Additionally,":[74],"we":[75],"demonstrate":[76],"how":[77],"combining":[78],"these":[79],"with":[81],"synthetic":[83],"generation":[85],"model":[86],"(TTS)":[87],"enables":[88],"accurate":[89],"detection":[90],"of":[91,98],"degradation,":[94],"ensuring":[95],"continuous":[96],"optimization":[97],"the":[99],"experience.":[102]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
