ABSTRACT
When a non-native speaker talks with a native speaker, he/she sometimes feels hard to take speaking turns due to language proficiency. The resulting conversation between a non-native speaker and a native speaker is not always productive. In this paper, we propose a conversational agent to support a non-native speaker in his/her second language conversation. The agent joins the conversation and makes intervention by a simple script based on turn-taking rules for taking the agent's turn, and gives the next turn to the non-native speaker for prompting him/her to speak. Evaluation of the proposed agent suggested that it successfully facilitated the non-native speaker's participation over 30% of the agent's interventions, and significantly increased the frequency of turn-taking.
- Zuengler Jane, 1993. Encouraging learners' conversational participation: The effect of content knowledge. In the Language Learning Journal Vol 43 No 3, 403--432.Google ScholarCross Ref
- Zhu Wei, 2001. Interaction and feedback in mixed peer response groups. In Journal of second language writing Vol 10 No 4, 251--276.Google Scholar
- Hautasaari Ari, and Naomi Yamashita, 2014. Catching up in audio conferences: highlighting keywords in ASR transcripts for non-native speakers. In Proceedings of the 5th ACM international conference on Collaboration across boundaries: culture, distance & technology. ACM, New York, NY, USA, 107--110. Google ScholarDigital Library
- Hanawa Hiromi, Xiaoyu Song, and Tomoo Inoue, 2016. Key-Typing on Teleconference: Collaborative Effort on CrossCultural Discussion. In Collaboration Technologies and Social Computing, CCIS vol 647, Springer, 74--88.Google Scholar
- Jing Ye, and Tomoo Inoue, 2016. A Speech Speed Awareness System for Non-Native Speakers. In Proceedings of the 19th ACM Conference on Computer Supported Cooperative Work and Social Computing Companion. ACM, New York, NY, USA, 49--52. Google ScholarDigital Library
- Yutaka Takase, Takashi Yoshino, and Yukiko I. Nakano, 2017. Conversational Robot with Conversation Coordination and Intervention Functionality in Multi-party Conversations. In IPSJ Journal Vol 58 No 5, 967--980.Google Scholar
- E. Goffman, 1981. Forms of Talk. University of Pennsylvania Press.Google Scholar
- Tomoo Inoue, Zixuan Guo, 2018. A conversational agent that uses turn-taking rules for supporting a non-native speaker. In Collaborative Technologies and Data Science in Smart City Applications , Logos, 1--9.Google Scholar
- Sacks Harvey, Emanuel A. Schegloff, and Gail Jefferson, 1974. A Simplest Systematics for the Organization of TurnTaking for Conversation. In Language Vol 50 No 4, 696--735.Google ScholarCross Ref
- Nakano Yukiko, and Yuki Fukuhara, 2012. Estimating conversational dominance in multiparty interaction. In Proceedings of the 14th ACM international conference on Multimodal interaction. ACM, New York, NY, USA, 77--84. Google ScholarDigital Library
- MMDAgent Homepage, http://www.mmdagent.jp/, last accessed 2018/02/01.Google Scholar
- Pyaudio Homepage, https://people.csail.mit.edu/hubert/pyaudio/docs/, last accessed 2018/02/01.Google Scholar
- Japanese-Language Proficiency Test, https://www.jlpt.jp/e/, last accessed 2019/02/13. DS IS RF NF Number of interventions 12 10 28 20 Rate 17 % % % %Google Scholar
Index Terms
- Using a Conversational Agent to Facilitate Non-native Speaker's Active Participation in Conversation
Recommendations
Conversational Error Analysis in Human-Agent Interaction
IVA '20: Proceedings of the 20th ACM International Conference on Intelligent Virtual AgentsConversational Agents (CAs) present many opportunities for changing how we interact with information and computer systems in a more natural, accessible way. Building on research in machine learning and HCI, it is now possible to design and test multi-...
Non-Native Speaker Identity Verification Based on Speech
ICNC '08: Proceedings of the 2008 Fourth International Conference on Natural Computation - Volume 06Speaker identity verification is an useful biometric recognition approach. Native speaker verification has achieved some better effects. But non-native speaker verification remains a challenging task because of wide varieties of non-native accents. ...
Accent neutralization for speech recognition of non-native speakers
iiWAS2019: Proceedings of the 21st International Conference on Information Integration and Web-based Applications & ServicesThese days, automatic speech recognition (ASR) systems achieve higher and higher accuracy rates. The score drops significantly, in case when the ASR system is being used with a non-native speaker of the language to be recognized. The main reason is ...
Comments