Kohei Hara’s research while affiliated with Kyoto University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (5)


A Job Interview Dialogue System with Autonomous Android ERICA
  • Chapter

March 2021

·

50 Reads

·

7 Citations

Lecture Notes in Electrical Engineering

·

Kohei Hara

·

·

[...]

·

We demonstrate a job interview dialogue with the autonomous android ERICA which plays the role of an interviewer. Conventional job interview dialogue systems ask only pre-defined questions. The job interview system of ERICA generates follow-up questions based on the interviewee’s response on the fly. The follow-up questions consist of two kinds of approaches: selection-based and keyword-based. The first type question is based on selection from a pre-defined question set, which can be used in many cases. The second type of question is based on a keyword extracted from the interviewee’s response, which digs into the interviewee’s response dynamically. These follow-up questions contribute to realizing natural and trained dialogue.



A Job Interview Dialogue System That Asks Follow-up Questions: Implementation and Evaluation with an Autonomous Android掘り下げ質問を行う就職面接対話システムの自律型アンドロイドでの実装と評価

September 2020

·

85 Reads

Transactions of the Japanese Society for Artificial Intelligence

A spoken dialogue system that plays the role of an interviewer for job interviews is presented. In this work, ourgoal is to implement an automated job interview system where candidates can use it as practice before the real interview.Conventional job interview systems ask only pre-defined questions, which make the dialogue monotonous andfar from human-human interviews. We propose follow-up question generation based on the assessment of candidateresponses and keyword extraction. This model was integrated into the dialogue system of the autonomous androidERICA to conduct subject experiments. The proposed job interview system was compared with the baseline systemthat did not generate any follow-up questions and selected among pre-defined questions. The experimental resultsshow that the proposed system is significantly better in subjective evaluations regarding impressions of job interviewpractice, the quality of questions, and the presence of the interviewer.



Citations (4)


... In the early research field on human-robot interaction, interactive capabilities were mainly used for information-providing tasks in real environments [6,13,21]. Recently, advances in autonomous conversational technologies such as natural speech synthesis and speech recognition have made it possible to handle more complex conversational tasks [14,23]. Social robots are expected to play a role in helping people solve their problems and mental health [8,15,18]. ...

Reference:

Practical Development of a Robot to Assist Cognitive Reconstruction in Psychiatric Day Care
A Job Interview Dialogue System with Autonomous Android ERICA
  • Citing Chapter
  • March 2021

Lecture Notes in Electrical Engineering

... We consider collaborative and competitive interaction game contexts and investigate both PBs and OBs during naturally occurring deception behaviour. Lastly, as social robots have begun to take on different social yet professional roles such as an interviewer [4,30], or a teacher [36], or a therapist [11] or a detective [24], we consider the Human-robot game interaction context and foresee a future where robots detect deception in real-time. The paper investigates the following research questions (RQs): ...

Job Interviewer Android with Elaborate Follow-up Question Generation
  • Citing Conference Paper
  • October 2020

... While [6] focuses on overlapping speech segments to study interruptions following a classification schema defined by [7] for French political interviews, interruptions may also occur without overlapping speech [8]. A better understanding of turn-taking also has implications for the development of human-machine interactions [9,10]. [11] has annotated TRPs in 8 hours of Slovak TV discussions and reports a binary classification accuracy of 94.4% with an ensemble model using fundamental frequency (F0) and intensity curves on chunks of 1.5 s. [12,13] propose an LSTM-based architecture using acoustic and linguistic features on English spontaneous dialogues to predict whether a speaker change would occur in the three following seconds. ...

Turn-Taking Prediction Based on Detection of Transition Relevance Place
  • Citing Conference Paper
  • September 2019

... Jain et al. [29] have constructed machine learning models that predict whether a listener's backchannel (short response) occurs based on the speaker's linguistic, acoustic, and visual features. Hara et al. [30] have constructed machine learning models that predict whether turn-taking occurs by considering backchannels and fillers based on the acoustic features of the user as the speaker and the robot (dialogue system) as the listener. Ishii et al. [31] have constructed machine learning models that predict whether backchannels and turn-taking occur based on the acoustic, linguistic, and visual features of the speaker and listener. ...

Prediction of Turn-taking Using Multitask Learning with Prediction of Backchannels and Fillers
  • Citing Conference Paper
  • September 2018