Takashi Maekaku

According to our database, Takashi Maekaku authored at least 14 papers between 2012 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model.

Takashi Maekaku, Jiatong Shi, Xuankai Chang, Yuya Fujita, Shinji Watanabe

CoRR, 2023

Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study.

Xuankai Chang, Brian Yan, Kwanghee Choi, Jee-Weon Jung, Yichen Lu, Soumi Maiti, Roshan S. Sharma, Jiatong Shi, Jinchuan Tian, Shinji Watanabe, Yuya Fujita, Takashi Maekaku, Pengcheng Guo, Yao-Fei Cheng, Pavel Denisov, Kohei Saijo, Hsiu-Hsuan Wang

CoRR, 2023

Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learning.

Xuankai Chang, Brian Yan, Yuya Fujita, Takashi Maekaku, Shinji Watanabe

CoRR, 2023

Fully Unsupervised Topic Clustering of Unlabelled Spoken Audio Using Self-Supervised Representation Learning and Topic Model.

Takashi Maekaku, Yuya Fujita, Xuankai Chang, Shinji Watanabe

Proceedings of the IEEE International Conference on Acoustics, 2023

LV-CTC: Non-Autoregressive ASR With CTC and Latent Variable Models.

Yuya Fujita, Shinji Watanabe, Xuankai Chang, Takashi Maekaku

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022

Attention Weight Smoothing Using Prior Distributions for Transformer-Based End-to-End ASR.

Takashi Maekaku, Yuya Fujita, Yifan Peng, Shinji Watanabe

Proceedings of the Interspeech 2022, 2022

End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation.

Xuankai Chang, Takashi Maekaku, Yuya Fujita, Shinji Watanabe

Proceedings of the Interspeech 2022, 2022

An Exploration of Hubert with Large Number of Cluster Units and Model Assessment Using Bayesian Information Criterion.

Takashi Maekaku, Xuankai Chang, Yuya Fujita, Shinji Watanabe

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021.

Takashi Maekaku, Xuankai Chang, Yuya Fujita, Li-Wei Chen, Shinji Watanabe, Alexander I. Rudnicky

Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition.

Xuankai Chang, Takashi Maekaku, Pengcheng Guo, Jing Shi, Yen-Ju Lu, Aswin Shanmugam Subramanian, Tianzi Wang, Shu-Wen Yang, Yu Tsao, Hung-yi Lee, Shinji Watanabe

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

2019

Simultaneous Detection and Localization of a Wake-Up Word Using Multi-Task Learning of the Duration and Endpoint.

Takashi Maekaku, Yusuke Kida, Akihiko Sugiyama

Proceedings of the Interspeech 2019, 2019

2013

Music classification applying Prime form and Interval-Class Vector.

Takashi Maekaku, Hiroyuki Kasai

Proceedings of the IEEE International Conference on Consumer Electronics, 2013

2012

Music relationship visualization based on melody piece transition using conditional divergence.

Takashi Maekaku, Hiroyuki Kasai

IEEE Trans. Consumer Electron., 2012

Music relationship visualization based on melody transition using Conditional Divergence for music browsing system.

Takashi Maekaku, Hiroyuki Kasai

Proceedings of the IEEE International Conference on Consumer Electronics, 2012