This paper proposes three novel and effective procedures for jointly analyzing repeated
utterances. First, we propose repetition-driven system switching, where repetition triggers …

We have developed the MPR multimodal dialogue corpus and describe research activities
using the corpus aimed for enabling multiparty human-robot verbal communication in real …

In spoken communications, correction utterances, which are utterances correcting other
participants utterances and behaviors, play crucial roles, and detecting them is one of the …

Significant increase in neural networks accuracy may not indicate that the system is able to
understand language phenomena that we, as humans, consider to be basic features of our …

Conversational agents (CAs), also known as chatbots or dialogue systems, are computer
programs that communicate with users in Natural Language (Jurafsky and Martin, 2019) …

This paper introduces a novel approach to auto-matically discover recurrent speech patterns
from multi-speaker corpus without a priori knowledge. The proposed approach is based on …

This report describes our ongoing attempt to evaluate the previously proposed method of
response obligation estimation [1] in a realtime human-robot interaction with a fully …

Response obligation is whether a spoken dialogue system should react to an input sound.
This paper focuses on the false negative errors in response obligation estimation (ROE) that …

COLLEGE OF ENGINEERING Page 1 -1- CHIN-HUI LEE PROFESSOR SCHOOL OF
ELECTRICAL AND COMPUTER ENGINEERING JANUARY 2018 I. EARNED DEGREES • Ph.D …

This thesis explores unsupervised algorithms for pattern discovery and retrieval in audio and
speech data. In this work, audio pattern is defined as repeating audio content such as …