Predicting synthetic voice style from facial expressions. An application for augmented conversations

Székely, íva; Ahmed, Zeeshan; Hennig, Shannon; Cabral, João P.; Carson-Berndsen, Julie

doi:10.1016/j.specom.2013.09.003

Cited by 4 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as Table 2 (column 3, rows 3 and 7) shows, research in this domain could benefit from more diverse types of UD such as voice and video, exploration of brand management in personal customer encounters (e.g., services) and enhanced theoretical developments (Table 3, column 4). Communication scholars create an automated synthetic vocal response system trained through unsupervised clustering of vocal source measures that adapts conveyed emotions in voice according to listener facial cues and text input to communicate an appropriate automated response (Székely et al 2014). Similar approaches in marketing could test the feasibility of automated customer service kiosks that analyze vocal cues in real time and inform staff when FLE assistance is needed to improve customer satisfaction and maintain brand management efforts.…”

Section: Marketing Intelligence For Value Creationmentioning

confidence: 99%

Unstructured data in marketing

Balducci

Marinova

2018

J. of the Acad. Mark. Sci.

192

140

View full text Add to dashboard Cite

The rise of unstructured data (UD), propelled by novel technologies, is reshaping markets and the management of marketing activities. Yet these increased data remain mostly untapped by many firms, suggesting the potential for further research developments. The integrative framework proposed in this study addresses the nature of UD and pursues theoretical richness and computational advancements by integrating insights from other disciplines. This article makes three main contributions to the literature by (1) offering a unifying definition and conceptualization of UD in marketing; (2) bridging disjoint literature with an organizing framework that synthesizes various subsets of UD relevant for marketing management through an integrative review; and (3) identifying substantive, computational, and theoretical gaps in extant literature and ways to leverage interdisciplinary knowledge to advance marketing research by applying UD analyses to underdeveloped areas.

show abstract

Section: Marketing Intelligence For Value Creationmentioning

confidence: 99%

Unstructured data in marketing

Balducci

Marinova

2018

J. of the Acad. Mark. Sci.

192

140

View full text Add to dashboard Cite

show abstract

“…Given that many people who use AAC also have impaired movement and dexterity, this kind of direct manipulation of speech sounds may not be appropriate. Some researchers have considered alternative ways to select tone of voices, for example, using facial expressions to control expressive speech synthesis ( Székely, Ahmed, Hennig, Cabral, & Carson-Berndsen, 2014 ). Further approaches that involve labeling or describing tones of voice might demand metalinguistic skills that some people with complex communication needs either do not have or have not yet developed.…”

Section: Exploring New Frontiers Of Tone Of Voicementioning

confidence: 99%

17 Ways to Say Yes: Toward Nuanced Tone of Voice in AAC and Speech Technology

Pullin

Hennig²

2015

Augmentative and Alternative Communication

Self Cite

View full text Add to dashboard Cite

People with complex communication needs who use speech-generating devices have very little expressive control over their tone of voice. Despite its importance in human interaction, the issue of tone of voice remains all but absent from AAC research and development however. In this paper, we describe three interdisciplinary projects, past, present and future: The critical design collection Six Speaking Chairs has provoked deeper discussion and inspired a social model of tone of voice; the speculative concept Speech Hedge illustrates challenges and opportunities in designing more expressive user interfaces; the pilot project Tonetable could enable participatory research and seed a research network around tone of voice. We speculate that more radical interactions might expand frontiers of AAC and disrupt speech technology as a whole.

show abstract

“…From processing and preparing the incoming audio [19,22,52] transcribing what was the user said [17,62], to understanding what the user meant [19] all have the goal of allowing users to speak naturally and fluently to a system in multiple complex contexts of use. From this point there is development focused on deciding what action the system should take as a result [1,23,24,41,60,61], what exactly the spoken response should be [10,26,27,31,45,48,57], and how that response should sound [10,14,32,46,56,66].…”

Section: Introductionmentioning

confidence: 99%

Leaving the Butler Behind: The Future of Role Reproduction in CUI

Jaber

2021

CUI 2021 - 3rd Conference on Conversational User Interfaces

View full text Add to dashboard Cite

Speech technologies are increasing in popularity by offering new interaction modalities for their users. Despite the prevalence of these devices, and the rapid improvement of the underlying technology, how we actually interact with these devices has remained wrapped up in the metaphors of command and control based around the problematic reproduction of the role of butler, maid, or personal assistant. In this paper we explore the issues around focusing our development and research on making a 'better' subordinate, and point to some opportunities to replace and refresh the status quo. CCS CONCEPTS• Human-centered computing → Natural language interfaces; Interaction design theory, concepts and paradigms; Interaction design process and methods.

show abstract

Predicting synthetic voice style from facial expressions. An application for augmented conversations

Cited by 4 publications

References 29 publications

Unstructured data in marketing

Unstructured data in marketing

17 Ways to Say Yes: Toward Nuanced Tone of Voice in AAC and Speech Technology

Leaving the Butler Behind: The Future of Role Reproduction in CUI

Contact Info

Product

Resources

About