arXiv subjects

Koji Inoue

Publications and source records attributed to Koji Inoue.

47 records · Page 3Linked to original sources

arXiv2024

Acknowledgment of Emotional States: Generating Validating Responses for Empathetic Dialogue

In the realm of human-AI dialogue, the facilitation of empathetic responses is important. Validation is one of the key communication techniques in psychology, which entails recognizing, understanding, and acknowledging others' emotional states, thoughts, and actions. This study introduces the first framework designed to engender empathetic dialogue with validating responses. Our approach incorporates a tripartite module system: 1) validation timing detection, 2) users' emotional state identification, and 3) validating response generation. Utilizing Japanese EmpatheticDialogues dataset - a textual-based dialogue dataset consisting of 8 emotional categories from Plutchik's wheel of emotions - the Task Adaptive Pre-Training (TAPT) BERT-based model outperforms both random baseline and the ChatGPT performance, in term of F1-score, in all modules. Further validation of our model's efficacy is confirmed in its application to the TUT Emotional Storytelling Corpus (TESC), a speech-based dialogue dataset, by surpassing both random baseline and the ChatGPT. This consistent performance across both textual and speech-based dialogues underscores the effectiveness of our framework in fostering empathetic human-AI communication.

cs.CL↗

arXiv2024

An Analysis of User Behaviors for Objectively Evaluating Spoken Dialogue Systems

Establishing evaluation schemes for spoken dialogue systems is important, but it can also be challenging. While subjective evaluations are commonly used in user experiments, objective evaluations are necessary for research comparison and reproducibility. To address this issue, we propose a framework for indirectly but objectively evaluating systems based on users' behaviors. In this paper, to this end, we investigate the relationship between user behaviors and subjective evaluation scores in social dialogue tasks: attentive listening, job interview, and first-meeting conversation. The results reveal that in dialogue tasks where user utterances are primary, such as attentive listening and job interview, indicators like the number of utterances and words play a significant role in evaluation. Observing disfluency also can indicate the effectiveness of formal tasks, such as job interview. On the other hand, in dialogue tasks with high interactivity, such as first-meeting conversation, behaviors related to turn-taking, like average switch pause length, become more important. These findings suggest that selecting appropriate user behaviors can provide valuable insights for objective evaluation in each social dialogue task.

cs.CL↗

arXiv2024

Real-time and Continuous Turn-taking Prediction Using Voice Activity Projection

A demonstration of a real-time and continuous turn-taking prediction system is presented. The system is based on a voice activity projection (VAP) model, which directly maps dialogue stereo audio to future voice activities. The VAP model includes contrastive predictive coding (CPC) and self-attention transformers, followed by a cross-attention transformer. We examine the effect of the input context audio length and demonstrate that the proposed system can operate in real-time with CPU settings, with minimal performance degradation.

cs.CL↗

arXiv2023

Inter-temperature Bandwidth Reduction in Cryogenic QAOA Machines

The bandwidth limit between cryogenic and room-temperature environments is a critical bottleneck in superconducting noisy intermediate-scale quantum computers. This paper presents the first trial of algorithm-aware system-level optimization to solve this issue by targeting the quantum approximate optimization algorithm. Our counter-based cryogenic architecture using single-flux quantum logic shows exponential bandwidth reduction and decreases heat inflow and peripheral power consumption of inter-temperature cables, which contributes to the scalability of superconducting quantum computers.

quant-ph↗

arXiv2023

Towards Objective Evaluation of Socially-Situated Conversational Robots: Assessing Human-Likeness through Multimodal User Behaviors

This paper tackles the challenging task of evaluating socially situated conversational robots and presents a novel objective evaluation approach that relies on multimodal user behaviors. In this study, our main focus is on assessing the human-likeness of the robot as the primary evaluation metric. While previous research often relied on subjective evaluations from users, our approach aims to evaluate the robot's human-likeness based on observable user behaviors indirectly, thus enhancing objectivity and reproducibility. To begin, we created an annotated dataset of human-likeness scores, utilizing user behaviors found in an attentive listening dialogue corpus. We then conducted an analysis to determine the correlation between multimodal user behaviors and human-likeness scores, demonstrating the feasibility of our proposed behavior-based evaluation method.

cs.CL↗

arXiv2023

Reasoning before Responding: Integrating Commonsense-based Causality Explanation for Empathetic Response Generation

Recent approaches to empathetic response generation try to incorporate commonsense knowledge or reasoning about the causes of emotions to better understand the user's experiences and feelings. However, these approaches mainly focus on understanding the causalities of context from the user's perspective, ignoring the system's perspective. In this paper, we propose a commonsense-based causality explanation approach for diverse empathetic response generation that considers both the user's perspective (user's desires and reactions) and the system's perspective (system's intentions and reactions). We enhance ChatGPT's ability to reason for the system's perspective by integrating in-context learning with commonsense knowledge. Then, we integrate the commonsense-based causality explanation with both ChatGPT and a T5-based model. Experimental evaluations demonstrate that our method outperforms other comparable methods on both automatic and human evaluations.

cs.CL↗

arXiv2022

Alzheimer's Dementia Detection through Spontaneous Dialogue with Proactive Robotic Listeners

As the aging of society continues to accelerate, Alzheimer's Disease (AD) has received more and more attention from not only medical but also other fields, such as computer science, over the past decade. Since speech is considered one of the effective ways to diagnose cognitive decline, AD detection from speech has emerged as a hot topic. Nevertheless, such approaches fail to tackle several key issues: 1) AD is a complex neurocognitive disorder which means it is inappropriate to conduct AD detection using utterance information alone while ignoring dialogue information; 2) Utterances of AD patients contain many disfluencies that affect speech recognition yet are helpful to diagnosis; 3) AD patients tend to speak less, causing dialogue breakdown as the disease progresses. This fact leads to a small number of utterances, which may cause detection bias. Therefore, in this paper, we propose a novel AD detection architecture consisting of two major modules: an ensemble AD detector and a proactive listener. This architecture can be embedded in the dialogue system of conversational robots for healthcare.

cs.RO↗

arXiv2021

Intelligent Conversational Android ERICA Applied to Attentive Listening and Job Interview

Following the success of spoken dialogue systems (SDS) in smartphone assistants and smart speakers, a number of communicative robots are developed and commercialized. Compared with the conventional SDSs designed as a human-machine interface, interaction with robots is expected to be in a closer manner to talking to a human because of the anthropomorphism and physical presence. The goal or task of dialogue may not be information retrieval, but the conversation itself. In order to realize human-level "long and deep" conversation, we have developed an intelligent conversational android ERICA. We set up several social interaction tasks for ERICA, including attentive listening, job interview, and speed dating. To allow for spontaneous, incremental multiple utterances, a robust turn-taking model is implemented based on TRP (transition-relevance place) prediction, and a variety of backchannels are generated based on time frame-wise prediction instead of IPU-based prediction. We have realized an open-domain attentive listening system with partial repeats and elaborating questions on focus words as well as assessment responses. It has been evaluated with 40 senior people, engaged in conversation of 5-7 minutes without a conversation breakdown. It was also compared against the WOZ setting. We have also realized a job interview system with a set of base questions followed by dynamic generation of elaborating questions. It has also been evaluated with student subjects, showing promising results.

cs.CL↗

arXiv2017

Detection of social signals for recognizing engagement in human-robot interaction

Detection of engagement during a conversation is an important function of human-robot interaction. The level of user engagement can influence the dialogue strategy of the robot. Our motivation in this work is to detect several behaviors which will be used as social signal inputs for a real-time engagement recognition model. These behaviors are nodding, laughter, verbal backchannels and eye gaze. We describe models of these behaviors which have been learned from a large corpus of human-robot interactions with the android robot ERICA. Input data to the models comes from a Kinect sensor and a microphone array. Using our engagement recognition model, we can achieve reasonable performance using the inputs from automatic social signal detection, compared to using manual annotation as input.

cs.HC↗

arXiv2017

Room-temperature 1.54 $μ$m photoluminescence of Er:O$_x$ centers at extremely low concentration in silicon

The demand for single photon sources at $λ~=~1.54~μ$m, which follows from the consistent development of quantum networks based on commercial optical fibers, makes Er:O$_x$ centers in Si still a viable resource thanks to the optical transition of $Er^{3+}~:~^4I_{13/2}~\rightarrow~^4I_{15/2}$. Yet, to date, the implementation of such system remains hindered by its extremely low emission rate. In this Letter, we explore the room-temperature photoluminescence (PL) at the telecomm wavelength of very low implantation doses of $Er:O_x$ in $Si$. The emitted photons, excited by a $λ~=~792~nm$ laser in both large areas and confined dots of diameter down to $5~μ$m, are collected by an inverted confocal microscope. The lower-bound number of detectable emission centers within our diffraction-limited illumination spot is estimated to be down to about 10$^4$, corresponding to an emission rate per individual ion of about $4~\times~10^{3}$ photons/s.

cond-mat.mtrl-sci↗

arXiv2007

Multi-physics Extension of OpenFMO Framework

OpenFMO framework, an open-source software (OSS) platform for Fragment Molecular Orbital (FMO) method, is extended to multi-physics simulations (MPS). After reviewing the several FMO implementations on distributed computer environments, the subsequent development planning corresponding to MPS is presented. It is discussed which should be selected as a scientific software, lightweight and reconfigurable form or large and self-contained form.

cs.DC↗