Takeshi Homma

Publication Activity (10 Years)

Years Active: 2003-2022
Publications (10 Years): 14

Top Topics

Multiple Classifiers

Speech Emotion Recognition

Source Separation

Top Venues

IEICE Trans. Inf. Syst.

J. Adv. Comput. Intell. Intell. Informatics

Publications

Natsuo Yamashita, Shota Horiguchi, Takeshi Homma
Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization. Odyssey (2022)
Natsuo Yamashita, Shota Horiguchi, Takeshi Homma
Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization. CoRR (2022)
Amalia Istiqlali Adiba, Takeshi Homma, Yasuhiro Sogawa
Unsupervised Domain Adaptation on Question-Answering System with Conversation Data. SIGDIAL (2022)
Naokazu Uchida, Takeshi Homma, Makoto Iwayama, Yasuhiro Sogawa
Reducing Offensive Replies in Open Domain Dialogue Systems. INTERSPEECH (2022)
Takeshi Homma, Qinghua Sun, Takuya Fujioka, Ryuta Takawaki, Eriko Ankyu, Kenji Nagamatsu, Daichi Sugawara, Etsuko T. Harada
Emotional Speech Synthesis for Companion Robot to Imitate Professional Caregiver Speech. CoRR (2021)
Amalia Istiqlali Adiba, Takeshi Homma, Toshinori Miyoshi
Towards Immediate Backchannel Generation Using Attention-Based Early Prediction Model. ICASSP (2021)
Takuya Fujioka, Takeshi Homma, Kenji Nagamatsu
Meta-Learning for Speech Emotion Recognition Considering Ambiguity of Emotion Labels. INTERSPEECH (2020)
Amalia Istiqlali Adiba, Takeshi Homma, Dario Bertero, Takashi Sumiyoshi, Kenji Nagamatsu
Delay Mitigation for Backchannel Prediction in Spoken Dialog System. IWSDS (2020)
Kazuaki Shima, Takeshi Homma, Masataka Motohashi, Rintaro Ikeshita, Hiroaki Kokubo, Yasunari Obuchi, Jinhua She
Efficient Corpus Creation Method for NLU Using Interview with Probing Questions. J. Adv. Comput. Intell. Intell. Informatics 23 (5) (2019)
Takuya Fujioka, Dario Bertero, Takeshi Homma, Kenji Nagamatsu
Addressing Ambiguity of Emotion Labels Through Meta-Learning. CoRR (2019)
Takeshi Homma, Yasunari Obuchi, Kazuaki Shima, Rintaro Ikeshita, Hiroaki Kokubo, Takuya Matsumoto
In-Vehicle Voice Interface with Improved Utterance Classification Accuracy Using Off-the-Shelf Cloud Speech Recognizer. IEICE Trans. Inf. Syst. (12) (2018)
Takeshi Homma, Adriano S. Arantes, Maria Teresa Gonzalez Diaz, Masahito Togami
Maximizing SLU Performance with Minimal Training Data Using Hybrid RNN Plus Rule-based Approach. SIGDIAL Conference (2018)
Takeshi Homma, Kazuaki Shima, Takuya Matsumoto
Robust utterance classification using multiple classifiers in the presence of speech recognition errors. SLT (2016)
Yusuke Fujita, Ryoichi Takashima, Takeshi Homma, Masahito Togami
Data Augmentation Using Multi-Input Multi-Output Source Separation for Deep Neural Network Based Acoustic Modeling. INTERSPEECH (2016)
Yusuke Fujita, Ryoichi Takashima, Takeshi Homma, Rintaro Ikeshita, Yohei Kawaguchi, Takashi Sumiyoshi, Takashi Endo, Masahito Togami
Unified ASR system using LGM-based source separation, noise-robust feature extraction, and word hypothesis selection. ASRU (2015)
Shuichi Ino, Takeshi Homma, Takashi Izumi
Psychophysical Measurement of Multiple Tactile Sensations Using a Broadband Vibrotactile Display. ISUC (2008)
Takeshi Homma, Shuichi Ino, Takashi Izumi, Hayato Kuroki, Tohru Ifukube
Measurement of Mechanical Characteristics of a Fingerpad Surface in the Design of a Tactile Display. J. Robotics Mechatronics 15 (2) (2003)