Building and Designing Expressive Speech Synthesis

Aylett, Matthew P.; Clark, Leigh; Cowan, Benjamin R.; Torre, Ilaria

doi:10.1145/3477322.3477329

Cited by 13 publications

(5 citation statements)

References 134 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This does not resemble the effects of the similarity attraction principle, however it falls in line with previous research with SIAs, that suggests that users prefer an agent speaking with a prestigious accent (see Aylett et al, 2021 for an overview).…”

Section: Discussionsupporting

confidence: 83%

“…Speech plays a crucial role when designing mixed-cultural SIAs. Speech does not only act as a way of explicit communication, but also as a way of transferring implicit information about the speaker, such as the emotional state, the state of health, its geographical or social background (Aylett et al, 2021). In contrast to the SIA's appearance and its non-verbal behaviour, which itself in most cases only gives cues about the SIA's intended original culture, speech has the ability to trigger the impression of a non-native speaking SIA, hence a mixed-cultural SIA (Obremski et al, 2021).…”

Section: Mixed-cultural Speech For Siasmentioning

confidence: 99%

“…In contrast to grammatical mistakes, accent has the potential to give more specific information about the speaker's geographical origin and to elicit stereotypes associated with that accent (Aylett et al, 2021;Ikeno and Hansen, 2007;Coupland and Bishop, 2007). While there are various approaches in social robotics focusing on the recognition of non-native user speech (Moussalli and Cardoso, 2017;Mubin et al, 2012;Irfan et al, 2020) there is very little research using non-native accents on the agent's side.…”

Section: Non-native Accentmentioning

confidence: 99%

“…Based on the theoretical background on the rating of ingroup members in the dimensions of warmth and competence (Fiske et al, 1999), the potential of speech eliciting stereotypes (Aylett et al, 2021;Ikeno and Hansen, 2007;Coupland and Bishop, 2007), as well as the German stereotypes of being hard working and trustworthy (Kohut et al, 2012;Kohut et al, 2013), we formulate the below hypotheses. Previous work has shown that different personality traits can act as predictors for the strength of the non-native accent a person retains when learning a new language (Zárate-Sández, 2017).…”

Section: Conclusion and Objectivementioning

confidence: 99%

“…Since speech is the primary channel of communication in human-human interaction (Nass and Brave, 2005), it is also very important when implementing (mixed-cultural) SIAs. Just as a SIA cannot be without a cultural background, intended or unintended, a SIA's speech always has certain characteristics such as a perceived accent or an underlying emotion, even if the voice is designed to be as neutral as possible (Aylett et al, 2021). Given the amount of implicit information transmitted through speech, it is predestined to be carefully attuned to the intended cultural background of a SIA.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

The impact of mixed-cultural speech on the stereotypical perception of a virtual robot

Obremski

Friedrich²,

Haak³

et al. 2022

Front. Robot. AI

View full text Add to dashboard Cite

Despite the fact that mixed-cultural backgrounds become of increasing importance in our daily life, the representation of multiple cultural backgrounds in one entity is still rare in socially interactive agents (SIAs). This paper’s contribution is twofold. First, it provides a survey of research on mixed-cultured SIAs. Second, it presents a study investigating how mixed-cultural speech (in this case, non-native accent) influences how a virtual robot is perceived in terms of personality, warmth, competence and credibility. Participants with English or German respectively as their first language watched a video of a virtual robot speaking in either standard English or German-accented English. It was expected that the German-accented speech would be rated more positively by native German participants as well as elicit the German stereotypes credibility and conscientiousness for both German and English participants. Contrary to the expectations, German participants rated the virtual robot lower in terms of competence and credibility when it spoke with a German accent, whereas English participants perceived the virtual robot with a German accent as more credible compared to the version without an accent. Both the native English and native German listeners classified the virtual robot with a German accent as significantly more neurotic than the virtual robot speaking standard English. This work shows that by solely implementing a non-native accent in a virtual robot, stereotypes are partly transferred. It also shows that the implementation of a non-native accent leads to differences in the perception of the virtual robot.

show abstract

Section: Discussionsupporting

confidence: 83%

Section: Mixed-cultural Speech For Siasmentioning

confidence: 99%