Any system using voice to communicate becomes personified by that voice. For robots, where the form and non-vocal behaviour also strongly personify the system, we can see a clash between the two technologies. The many challenges in building responsive and interactive robots mean that language systems are often designed in a vacuum and when they are finally brought together can ruin the look, feel and sound of the completed system. This problem is intensified by natural language processing technology which can further add inappropriate behaviours following mythical business use cases, rather than exploring how users really would like to relate and use embodied artificial systems. In this positional paper, we present two studies in robot voice design and a non-vocal use case of the Honda Research Institute robot Haru. Finally, we ask the question what sort of voice should Haru have?
{"title":"The right kind of unnatural: designing a robot voice","authors":"M. Aylett, S. Sutton, Yolanda Vazquez-Alvarez","doi":"10.1145/3342775.3342806","DOIUrl":"https://doi.org/10.1145/3342775.3342806","url":null,"abstract":"Any system using voice to communicate becomes personified by that voice. For robots, where the form and non-vocal behaviour also strongly personify the system, we can see a clash between the two technologies. The many challenges in building responsive and interactive robots mean that language systems are often designed in a vacuum and when they are finally brought together can ruin the look, feel and sound of the completed system. This problem is intensified by natural language processing technology which can further add inappropriate behaviours following mythical business use cases, rather than exploring how users really would like to relate and use embodied artificial systems. In this positional paper, we present two studies in robot voice design and a non-vocal use case of the Honda Research Institute robot Haru. Finally, we ask the question what sort of voice should Haru have?","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121030142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This provocation paper calls for a deeper understanding of what spoken human-computer interaction is, and what it can be. Its given structure by a story of humanlikeness and fraudulent spoken dialogue systems - specifically systems that deliberately attempts to mislead their interlocutors into believing that they are speaking to a human. Against this backdrop, a plea that conversational user interfaces are viewed from the perspective of conversation and spoken interaction first, and from the perspective of GUIs and interface design second, lest we impose the limitations of one field onto the possibilities of another, rather than the other way around.
{"title":"Shoehorning in the name of science","authors":"Jens Edlund","doi":"10.1145/3342775.3342794","DOIUrl":"https://doi.org/10.1145/3342775.3342794","url":null,"abstract":"This provocation paper calls for a deeper understanding of what spoken human-computer interaction is, and what it can be. Its given structure by a story of humanlikeness and fraudulent spoken dialogue systems - specifically systems that deliberately attempts to mislead their interlocutors into believing that they are speaking to a human. Against this backdrop, a plea that conversational user interfaces are viewed from the perspective of conversation and spoken interaction first, and from the perspective of GUIs and interface design second, lest we impose the limitations of one field onto the possibilities of another, rather than the other way around.","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125844556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With an ever-increasing amount of information and ever-more-hectic lifestyles, many people rely on news briefs to stay up to date. Consequently, the reliance on single-source media narratives can lead to a biased and narrow perception of the world. Conversational interfaces, as a medium for delivering news stories, can help to address this problem by encouraging users to explore information resources and news stories by formulating curiosity driven comments and questions. We propose Inquisitive Mind (IM) - a conversational companion that proactively points out different narratives of the story, refers users to source materials, and encourages deeper exploration of the topic. We argue that IM could foster curiosity, encourage critical thinking, and effectively lead to more conscious media consumption.
{"title":"Inquisitive mind: a conversational news companion","authors":"Mateusz Dubiel, Alessandra Cervone, G. Riccardi","doi":"10.1145/3342775.3342802","DOIUrl":"https://doi.org/10.1145/3342775.3342802","url":null,"abstract":"With an ever-increasing amount of information and ever-more-hectic lifestyles, many people rely on news briefs to stay up to date. Consequently, the reliance on single-source media narratives can lead to a biased and narrow perception of the world. Conversational interfaces, as a medium for delivering news stories, can help to address this problem by encouraging users to explore information resources and news stories by formulating curiosity driven comments and questions. We propose Inquisitive Mind (IM) - a conversational companion that proactively points out different narratives of the story, refers users to source materials, and encourages deeper exploration of the topic. We argue that IM could foster curiosity, encourage critical thinking, and effectively lead to more conscious media consumption.","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131914279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The 'wake word' can be considered one of the features that hinder natural conversation. Recently, tech companies such as Google and Amazon have developed features that enable the user to communicate with the virtual agent without a wake word. With this type of feature, conversation with a voice agent could be more natural, like Human-Human Conversation (HHC). However, the elimination of the wake word in a Voice User Interface (VUI) should be considered carefully, as it is perceived by users not only as technical feature, but also as a contextual feature. In this paper, we conducted a preliminary user study to understand how people use a wake word while interacting with their voice agent. We found out that users felt that they took control of the conversation with the voice agent by using the wake word. Furthermore, they tended to project negative feeling onto the wake word, because they usually convey negative with the wake word (e.g., to reset a failed conversation). Based on these findings, we discuss the contextual meaning of the wake word from the perspective of VUI design.
{"title":"Finding contextual meaning of the wake word","authors":"Hyunhoon Jung, Hyeji Kim","doi":"10.1145/3342775.3342805","DOIUrl":"https://doi.org/10.1145/3342775.3342805","url":null,"abstract":"The 'wake word' can be considered one of the features that hinder natural conversation. Recently, tech companies such as Google and Amazon have developed features that enable the user to communicate with the virtual agent without a wake word. With this type of feature, conversation with a voice agent could be more natural, like Human-Human Conversation (HHC). However, the elimination of the wake word in a Voice User Interface (VUI) should be considered carefully, as it is perceived by users not only as technical feature, but also as a contextual feature. In this paper, we conducted a preliminary user study to understand how people use a wake word while interacting with their voice agent. We found out that users felt that they took control of the conversation with the voice agent by using the wake word. Furthermore, they tended to project negative feeling onto the wake word, because they usually convey negative with the wake word (e.g., to reset a failed conversation). Based on these findings, we discuss the contextual meaning of the wake word from the perspective of VUI design.","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116076450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Large, L. Clark, G. Burnett, Kyle Harrington, J. Luton, Peter Thomas, P. Bennett
The use of speech has been popularised as a human-vehicle interface in the automotive domain. While this is most often associated with alleviating concerns of driver distraction and cognitive load, the study explores whether the presence of conversation could, in and of itself, engender trust in the technology, based on our understanding of speech in humans. Thirty-four participants were transported in a fully-autonomous, self-driving 'pod' vehicle, accompanied by a natural-language, conversational interface ('UltraCab'), which was delivered using Wizard-of-Oz methodology. Emergent, trust-related themes were identified from the conversation that took place between participants and UltraCab, posing the question of whether participants sought an emotional connection with the vehicle, or whether conversation remained primarily functional. Implications for trust and the design of conversational interfaces are discussed.
{"title":"\"It's small talk, jim, but not as we know it.\": engendering trust through human-agent conversation in an autonomous, self-driving car","authors":"D. Large, L. Clark, G. Burnett, Kyle Harrington, J. Luton, Peter Thomas, P. Bennett","doi":"10.1145/3342775.3342789","DOIUrl":"https://doi.org/10.1145/3342775.3342789","url":null,"abstract":"The use of speech has been popularised as a human-vehicle interface in the automotive domain. While this is most often associated with alleviating concerns of driver distraction and cognitive load, the study explores whether the presence of conversation could, in and of itself, engender trust in the technology, based on our understanding of speech in humans. Thirty-four participants were transported in a fully-autonomous, self-driving 'pod' vehicle, accompanied by a natural-language, conversational interface ('UltraCab'), which was delivered using Wizard-of-Oz methodology. Emergent, trust-related themes were identified from the conversation that took place between participants and UltraCab, posing the question of whether participants sought an emotional connection with the vehicle, or whether conversation remained primarily functional. Implications for trust and the design of conversational interfaces are discussed.","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121056983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper we try to provoke by teasing the question "if conversational user interfaces should be multimodal?". Of course they should! In decades of research in multimodal HCI excellent arguments can be found. We substantiate our perspective with an example showing how conversational interaction becomes more robust and efficient through the use of multimodality.
{"title":"Conversation is multimodal: thus conversational user interfaces should be as well","authors":"Stefan Schaffer, Norbert Reithinger","doi":"10.1145/3342775.3342801","DOIUrl":"https://doi.org/10.1145/3342775.3342801","url":null,"abstract":"In this paper we try to provoke by teasing the question \"if conversational user interfaces should be multimodal?\". Of course they should! In decades of research in multimodal HCI excellent arguments can be found. We substantiate our perspective with an example showing how conversational interaction becomes more robust and efficient through the use of multimodality.","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"382 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122922519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Companies are increasingly using chatbots to provide customer service. Despite this trend, little in-depth research has been conducted on user experience and user motivation for this important application area of conversational interfaces. To close this research gap, we interviewed 24 users of two chatbots for customer service. Our results demonstrate the importance of such chatbots to efficiently provide adequate answers in response to simple enquiries. However, our results also show that the occasional lack of adequate answers does not necessarily produce a bad experience, as long as the chatbot offers an easy path for follow-up with human customer service representatives. In contrast to what is suggested in the existing literature on users' perceptions of conversational agents, this study's participants demonstrated realistic expectations of the chatbots' capabilities. Furthermore, we found that the human likeness of chatbots for customer service, while potentially of some relevance for user experience, is dwarfed in importance compared to such chatbots' ability to efficiently and adequately handle enquiries. As such, our findings serve to complement and extend current knowledge. On the basis of our findings, we suggest implications for theory and practice and point out avenues for future research.
{"title":"Chatbots for customer service: user experience and motivation","authors":"Asbjørn Følstad, Marita Skjuve","doi":"10.1145/3342775.3342784","DOIUrl":"https://doi.org/10.1145/3342775.3342784","url":null,"abstract":"Companies are increasingly using chatbots to provide customer service. Despite this trend, little in-depth research has been conducted on user experience and user motivation for this important application area of conversational interfaces. To close this research gap, we interviewed 24 users of two chatbots for customer service. Our results demonstrate the importance of such chatbots to efficiently provide adequate answers in response to simple enquiries. However, our results also show that the occasional lack of adequate answers does not necessarily produce a bad experience, as long as the chatbot offers an easy path for follow-up with human customer service representatives. In contrast to what is suggested in the existing literature on users' perceptions of conversational agents, this study's participants demonstrated realistic expectations of the chatbots' capabilities. Furthermore, we found that the human likeness of chatbots for customer service, while potentially of some relevance for user experience, is dwarfed in importance compared to such chatbots' ability to efficiently and adequately handle enquiries. As such, our findings serve to complement and extend current knowledge. On the basis of our findings, we suggest implications for theory and practice and point out avenues for future research.","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114119708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Patrik Jonell, Per Fallgren, Fethiye Irmak Dogan, José Lopes, Ulme Wennberg, Gabriel Skantze
In this paper we present a crowdsourcing-based approach for collecting dialog data for a social chat dialog system, which gradually builds a dialog graph from actual user responses and crowd-sourced system answers, conditioned by a given persona and other instructions. This approach was tested during the second instalment of the Amazon Alexa Prize 2018 (AP2018), both for the data collection and to feed a simple dialog system which would use the graph to provide answers. As users interacted with the system, a graph which maintained the structure of the dialogs was built, identifying parts where more coverage was needed. In an offline evaluation, we have compared the corpus collected during the competition with other potential corpora for training chatbots, including movie subtitles, online chat forums and conversational data. The results show that the proposed methodology creates data that is more representative of actual user utterances, and leads to more coherent and engaging answers from the agent. An implementation of the proposed method is available as open-source code.
{"title":"Crowdsourcing a self-evolving dialog graph","authors":"Patrik Jonell, Per Fallgren, Fethiye Irmak Dogan, José Lopes, Ulme Wennberg, Gabriel Skantze","doi":"10.1145/3342775.3342790","DOIUrl":"https://doi.org/10.1145/3342775.3342790","url":null,"abstract":"In this paper we present a crowdsourcing-based approach for collecting dialog data for a social chat dialog system, which gradually builds a dialog graph from actual user responses and crowd-sourced system answers, conditioned by a given persona and other instructions. This approach was tested during the second instalment of the Amazon Alexa Prize 2018 (AP2018), both for the data collection and to feed a simple dialog system which would use the graph to provide answers. As users interacted with the system, a graph which maintained the structure of the dialogs was built, identifying parts where more coverage was needed. In an offline evaluation, we have compared the corpus collected during the competition with other potential corpora for training chatbots, including movie subtitles, online chat forums and conversational data. The results show that the proposed methodology creates data that is more representative of actual user utterances, and leads to more coherent and engaging answers from the agent. An implementation of the proposed method is available as open-source code.","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"38 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132953695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In "Our Friends Electric"* Rogers et al. [4] advocate for internet health by exploring preferable future scenarios for voice enabled internet technologies. The fictional designs in the film were developed from 4 position statements that reflect a core set of values by which to measure internet health. In this provocation, one of these position statements is taken and used to propose a preferable near-present scenario; a small design change to current voice assistants that acknowledges the contributions that nations and their peoples make to the production of the voice enabled internet. Finally, envisioning this design change reveals the potential for the internet to provide an openness and neutrality that the real-world cannot.
{"title":"\"I am from all over the world\": moving towards a healthier voice enabled internet by acknowledging how it is built","authors":"S. Sutton","doi":"10.1145/3342775.3342798","DOIUrl":"https://doi.org/10.1145/3342775.3342798","url":null,"abstract":"In \"Our Friends Electric\"* Rogers et al. [4] advocate for internet health by exploring preferable future scenarios for voice enabled internet technologies. The fictional designs in the film were developed from 4 position statements that reflect a core set of values by which to measure internet health. In this provocation, one of these position statements is taken and used to propose a preferable near-present scenario; a small design change to current voice assistants that acknowledges the contributions that nations and their peoples make to the production of the voice enabled internet. Finally, envisioning this design change reveals the potential for the internet to provide an openness and neutrality that the real-world cannot.","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121675430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Fischer, S. Reeves, Martin Porcheron, R. Sikveland
Drawing from Conversation Analysis (CA), we examine how the orientation towards progressivity in talk-keeping things moving-might help us better understand and design for voice interactions. We introduce progressivity by surveying its explication in CA, and then look at how a strong preference for progressivity in conversation works out practically in sequences of voice interaction recorded in people's homes. Following Stivers and Robinson's work on progressivity, we find our data shows: how non-answer responses impede progress; how accounts offered for non-answer responses can lead to recovery; how participants work to receive answers; and how, ultimately, moving the interaction forwards does not necessarily involve a fitted answer, but other kinds of responses as well. We discuss the wider potential of applying progressivity to evaluate and understand voice interactions, and consider what designers of voice experiences might do to design for progressivity. Our contribution is a demonstration of the progressivity principle and its interactional features, which also points towards the need for specific kinds of future developments in speech technology.
{"title":"Progressivity for voice interface design","authors":"J. Fischer, S. Reeves, Martin Porcheron, R. Sikveland","doi":"10.1145/3342775.3342788","DOIUrl":"https://doi.org/10.1145/3342775.3342788","url":null,"abstract":"Drawing from Conversation Analysis (CA), we examine how the orientation towards progressivity in talk-keeping things moving-might help us better understand and design for voice interactions. We introduce progressivity by surveying its explication in CA, and then look at how a strong preference for progressivity in conversation works out practically in sequences of voice interaction recorded in people's homes. Following Stivers and Robinson's work on progressivity, we find our data shows: how non-answer responses impede progress; how accounts offered for non-answer responses can lead to recovery; how participants work to receive answers; and how, ultimately, moving the interaction forwards does not necessarily involve a fitted answer, but other kinds of responses as well. We discuss the wider potential of applying progressivity to evaluate and understand voice interactions, and consider what designers of voice experiences might do to design for progressivity. Our contribution is a demonstration of the progressivity principle and its interactional features, which also points towards the need for specific kinds of future developments in speech technology.","PeriodicalId":408689,"journal":{"name":"Proceedings of the 1st International Conference on Conversational User Interfaces","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134236885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：