Automated speech recognition (ASR) converts language into text and is used across a variety of ap... more Automated speech recognition (ASR) converts language into text and is used across a variety of applications to assist us in everyday life, from powering virtual assistants, natural language conversations, to enabling dictation services. While recent work suggests that there are racial disparities in the performance of ASR systems for speakers of African American Vernacular English, little is known about the psychological and experiential effects of these failures paper provides a detailed examination of the behavioral and psychological consequences of ASR voice errors and the difficulty African American users have with getting their intents recognized. The results demonstrate that ASR failures have a negative, detrimental impact on African American users. Specifically, African Americans feel othered when using technology powered by ASR—errors surface thoughts about identity, namely about race and geographic location—leaving them feeling that the technology was not made for them. As ...
Proceedings of the Cognitive Science Society, 2018
Phonological characteristics of a voice, such as th-stopping (pronouncing them as " dem ") associ... more Phonological characteristics of a voice, such as th-stopping (pronouncing them as " dem ") associated with African American English (AAE), provide indexical sociolinguistic information about the speaker. Word usage also signals this social dialect, i.e. usage of crib to mean house. The current study examines the effect of these sociolinguistic characteristics on word recall, as well as the interaction between the phonological and the lexical levels of variation. In a modified word recognition task, listeners displayed more accurate veridical word recall of AAE lexical items and voices. Furthermore, there was an interaction between phonological and lexical variation: listeners were even more accurate at recognizing AAE-specific lexical items heard in an AAE voice. This study adds to a growing body of work finding that sociolinguistic information influences word memory.
Automated speech recognition (ASR) converts language into text and is used across a variety of ap... more Automated speech recognition (ASR) converts language into text and is used across a variety of applications to assist us in everyday life, from powering virtual assistants, natural language conversations, to enabling dictation services. While recent work suggests that there are racial disparities in the performance of ASR systems for speakers of African American Vernacular English, little is known about the psychological and experiential effects of these failures paper provides a detailed examination of the behavioral and psychological consequences of ASR voice errors and the difficulty African American users have with getting their intents recognized. The results demonstrate that ASR failures have a negative, detrimental impact on African American users. Specifically, African Americans feel othered when using technology powered by ASR—errors surface thoughts about identity, namely about race and geographic location—leaving them feeling that the technology was not made for them. As ...
Proceedings of the Cognitive Science Society, 2018
Phonological characteristics of a voice, such as th-stopping (pronouncing them as " dem ") associ... more Phonological characteristics of a voice, such as th-stopping (pronouncing them as " dem ") associated with African American English (AAE), provide indexical sociolinguistic information about the speaker. Word usage also signals this social dialect, i.e. usage of crib to mean house. The current study examines the effect of these sociolinguistic characteristics on word recall, as well as the interaction between the phonological and the lexical levels of variation. In a modified word recognition task, listeners displayed more accurate veridical word recall of AAE lexical items and voices. Furthermore, there was an interaction between phonological and lexical variation: listeners were even more accurate at recognizing AAE-specific lexical items heard in an AAE voice. This study adds to a growing body of work finding that sociolinguistic information influences word memory.
Uploads
Papers by Zion Mengesha