Takeshi Homma

Orcid: 0000-0003-3864-3848

According to our database1, Takeshi Homma authored at least 16 papers between 2003 and 2022.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2022
Unsupervised Domain Adaptation on Question-Answering System with Conversation Data.
Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2022

Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization.
Proceedings of the Odyssey 2022: The Speaker and Language Recognition Workshop, 28 June, 2022

Reducing Offensive Replies in Open Domain Dialogue Systems.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

2021
Emotional Speech Synthesis for Companion Robot to Imitate Professional Caregiver Speech.
CoRR, 2021

Towards Immediate Backchannel Generation Using Attention-Based Early Prediction Model.
Proceedings of the IEEE International Conference on Acoustics, 2021

2020
Delay Mitigation for Backchannel Prediction in Spoken Dialog System.
Proceedings of the Conversational Dialogue Systems for the Next Decade, 2020

Meta-Learning for Speech Emotion Recognition Considering Ambiguity of Emotion Labels.
Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

2019
Efficient Corpus Creation Method for NLU Using Interview with Probing Questions.
J. Adv. Comput. Intell. Intell. Informatics, 2019

Addressing Ambiguity of Emotion Labels Through Meta-Learning.
CoRR, 2019

2018
In-Vehicle Voice Interface with Improved Utterance Classification Accuracy Using Off-the-Shelf Cloud Speech Recognizer.
IEICE Trans. Inf. Syst., 2018

Maximizing SLU Performance with Minimal Training Data Using Hybrid RNN Plus Rule-based Approach.
Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, 2018

2016
Robust utterance classification using multiple classifiers in the presence of speech recognition errors.
Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

Data Augmentation Using Multi-Input Multi-Output Source Separation for Deep Neural Network Based Acoustic Modeling.
Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

2015
Unified ASR system using LGM-based source separation, noise-robust feature extraction, and word hypothesis selection.
Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015

2008
Psychophysical Measurement of Multiple Tactile Sensations Using a Broadband Vibrotactile Display.
Proceedings of the ISUC 2008, 2008

2003
Measurement of Mechanical Characteristics of a Fingerpad Surface in the Design of a Tactile Display.
J. Robotics Mechatronics, 2003


  Loading...