This study examines the performance of a smartphone-based automatic speech recognition(ASR) system when processing diverse English accents. With the increasing reliance on voiceactivatedartificial intelligence in daily tasks, ensuring equitable ASR performance across linguisticvarieties is critical. Using audio data from the CIRCE project corpus, we assess recognitionaccuracy for eleven English accents selected according to Kachru’s three-circle model (Inner,Outer, and Expanding Circle varieties). Findings highlight disparities in recognition performanceand suggest that ASR models exhibit a bias favoring American English (AmE). Thestudy underscores the need for enhanced ASR inclusivity and diversification of training data.
Assessing Smartphone Speech Recognition Across Diverse English Accents: A Preliminary Study
Soria, Claudia
Primo
Conceptualization
;
2025
Abstract
This study examines the performance of a smartphone-based automatic speech recognition(ASR) system when processing diverse English accents. With the increasing reliance on voiceactivatedartificial intelligence in daily tasks, ensuring equitable ASR performance across linguisticvarieties is critical. Using audio data from the CIRCE project corpus, we assess recognitionaccuracy for eleven English accents selected according to Kachru’s three-circle model (Inner,Outer, and Expanding Circle varieties). Findings highlight disparities in recognition performanceand suggest that ASR models exhibit a bias favoring American English (AmE). Thestudy underscores the need for enhanced ASR inclusivity and diversification of training data.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.ancejournal | L'ANALISI LINGUISTICA E LETTERARIA | en |
| dc.authority.orgunit | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | en |
| dc.authority.people | Soria, Claudia | en |
| dc.authority.people | Nodari, Rosalba | en |
| dc.authority.people | Calamai, Silvia | en |
| dc.authority.project | erasmusplus_::db8296b8cd3818378dfdefab894ef273 | en |
| dc.collection.id.s | b3f88f24-048a-4e43-8ab1-6697b90e068e | * |
| dc.collection.name | 01.01 Articolo in rivista | * |
| dc.contributor.appartenenza | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | * |
| dc.contributor.appartenenza.mi | 918 | * |
| dc.contributor.area | Non assegn | * |
| dc.date.firstsubmission | 2026/03/04 13:02:02 | * |
| dc.date.issued | 2025 | - |
| dc.date.submission | 2026/03/04 13:02:02 | * |
| dc.description.abstracteng | This study examines the performance of a smartphone-based automatic speech recognition(ASR) system when processing diverse English accents. With the increasing reliance on voiceactivatedartificial intelligence in daily tasks, ensuring equitable ASR performance across linguisticvarieties is critical. Using audio data from the CIRCE project corpus, we assess recognitionaccuracy for eleven English accents selected according to Kachru’s three-circle model (Inner,Outer, and Expanding Circle varieties). Findings highlight disparities in recognition performanceand suggest that ASR models exhibit a bias favoring American English (AmE). Thestudy underscores the need for enhanced ASR inclusivity and diversification of training data. | - |
| dc.description.allpeople | Soria, Claudia; Nodari, Rosalba; Calamai, Silvia | - |
| dc.description.allpeopleoriginal | Soria, Claudia; Nodari, Rosalba; Calamai, Silvia | en |
| dc.description.fulltext | none | en |
| dc.description.numberofauthors | 3 | - |
| dc.identifier.doi | 10.69117/ALL.2025.3.04 | en |
| dc.identifier.source | medra | * |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/571034 | - |
| dc.language.iso | eng | en |
| dc.relation.issue | 3 | en |
| dc.relation.projectAcronym | - | en |
| dc.relation.projectAwardNumber | 2022-1-IT02-KA220-SCH-000087602 | en |
| dc.relation.projectAwardTitle | Counteracting accent dIscrimination pRactiCes in Education | en |
| dc.relation.projectFunderName | European Commission | en |
| dc.relation.projectFundingStream | ERASMUS+ | en |
| dc.relation.volume | 33 | en |
| dc.subject.keywordseng | Automatic Speech Recognition, Smartphone, English Accents, Sociophonetics | - |
| dc.subject.singlekeyword | Automatic Speech Recognition | * |
| dc.subject.singlekeyword | Smartphone | * |
| dc.subject.singlekeyword | English Accents | * |
| dc.subject.singlekeyword | Sociophonetics | * |
| dc.title | Assessing Smartphone Speech Recognition Across Diverse English Accents: A Preliminary Study | en |
| dc.type.driver | info:eu-repo/semantics/article | - |
| dc.type.full | 01 Contributo su Rivista::01.01 Articolo in rivista | it |
| dc.type.impactfactor | si | en |
| dc.type.miur | 262 | - |
| dc.type.referee | Esperti anonimi | en |
| iris.orcid.lastModifiedDate | 2026/03/04 13:02:02 | * |
| iris.orcid.lastModifiedMillisecond | 1772625722317 | * |
| iris.sitodocente.maxattempts | 1 | - |
| iris.unpaywall.metadataCallLastModified | 05/03/2026 05:00:23 | - |
| iris.unpaywall.metadataCallLastModifiedMillisecond | 1772683223165 | - |
| iris.unpaywall.metadataErrorDescription | 0 | - |
| iris.unpaywall.metadataErrorType | ERROR_NO_MATCH | - |
| iris.unpaywall.metadataStatus | ERROR | - |
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
