Yoshinao Sato

Publication Activity (10 Years)

Years Active: 2018-2023
Publications (10 Years): 13

Top Topics

Domain Adaptation

Supervised Learning

Speech Emotion Recognition

Top Venues

Publications

Zhi Zhu, Yoshinao Sato
Domain Adaptation without Catastrophic Forgetting on a Small-Scale Partially-Labeled Corpus for Speech Emotion Recognition. ICASSP (2023)
Conggui Liu, Yoshinao Sato
A Voice-Activity-Aware Loss Function for Continuous Speech Separation. MMSP (2023)
Zhi Zhu, Yoshinao Sato
Deep Investigation of Intermediate Representations in Self-Supervised Learning Models for Speech Emotion Recognition. ICASSP Workshops (2023)
Yoshinao Sato, Kouki Miyazawa
Statistical quality estimation for partially subjective classification tasks through crowdsourcing. Lang. Resour. Evaluation 57 (1) (2023)
Yoshinao Sato, Narumitsu Ikeda, Hirokazu Takahashi
Shuffleaugment: A Data Augmentation Method Using Time Shuffling. ICASSP (2023)
Takahiro Kamatani, Yoshinao Sato, Masato Fujino
Ghost Play - A Violin-Playing Robot using Electromagnetic Linear Actuators. NIME (2022)
Conggui Liu, Yoshinao Sato
Enhancing Block-Online Speech Separation using Interblock Context Flow. MMSP (2021)
Zhi Zhu, Yoshinao Sato
Speech Emotion Recognition Using Semi-Supervised Learning with Efficient Labeling Strategies. ASRU (2021)
Delowar Hossain, Yoshinao Sato
Efficient corpus design for wake-word detection. SLT (2021)
Yoshinao Sato, Kouki Miyazawa
Quality Estimation for Partially Subjective Classification Tasks via Crowdsourcing. LREC (2020)
Zhi Zhu, Yoshinao Sato
Reconciliation of Multiple Corpora for Speech Emotion Recognition by Multiple Classifiers with an Adversarial Corpus Discriminator. INTERSPEECH (2020)
Conggui Liu, Yoshinao Sato
Self-Attention for Multi-Channel Speech Separation in Noisy and Reverberant Environments. APSIPA (2020)
Narumitsu Ikeda, Yoshinao Sato, Hirokazu Takahashi
Short Utterance Speaker Recognition by Reservoir with Self-Organized Mapping. SLT (2018)