HA3CI Publications

　　　　　　　　　　


Past publications (before October 2021) can be found here.
　　　　　　　　　　
招待講演・Invited Talks
  1. [Invited Speaker] S. Sakti, "Semi-supervised Learning for Low-resource Multilingual and Multimodal Speech Processing with Machine Speech Chain" [A joint work with A. Tjandra, J. Effendi, S. Novitasari, S. Nakayama, T. Yanagita, S. Nakamura (NAIST/RIKEN AIP, Japan)], HiTZ Language Technology Webinar, May 5th, 2022
  2. [Invited Speaker] S. Sakti, "Self-Adaptive Machine Speech Chain in Noisy Environment" [A joint work with A. Tjandra, J. Effendi, S. Novitasari, S. Nakamura (NAIST/RIKEN AIP, Japan)], The AAAI workshop on Self-supervised Learning for Audio and Speech Processing, Feb 28th, 2022
  3. [Invited Speaker] S. Sakti, "Machine Speech Chain: A Deep Learning Approach for Modeling Human Speech Perception and Production with Auditory Feedback Mechanism" [A joint work with A. Tjandra, J. Effendi, S. Novitasari, S. Nakamura (NAIST/RIKEN AIP, Japan)], The ITB Seminar, Dec 24th, 2021
  4. [Keynote speaker] S. Sakti, "Machine Speech Chain: A Deep Learning Approach for Training and Inference through Feedback Loop" [A joint work with A. Tjandra, J. Effendi, S. Novitasari, S. Nakamura (NAIST/RIKEN AIP, Japan)], the IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Cartagena, Colombia, Dec 15th, 2021
  5. [Keynote speaker] S. Sakti, "Listening while Speaking and Visualizing: A Semi-supervised Approach with Multimodal Machine Speech Chain" [A joint work with A. Tjandra, J. Effendi, S. Novitasari, S. Nakamura (NAIST/RIKEN AIP, Japan)], the SoCS International Seminar, Dec 10tn, 2021
  6. [Keynote speaker] S. Sakti, "Listening while Speaking and Visualizing: A Semi-supervised Approach with Multimodal Machine Speech Chain" [A joint work with A. Tjandra, J. Effendi, S. Novitasari, S. Nakamura (NAIST/RIKEN AIP, Japan)], the International Conference of Artificial Intelligence and Speech Technology (AIST), Nov 13th, 2021
査読つき論文・Peer-reviewed Journal
  1. 柳田 智也, サクティ サクリアニ, 中村 哲, "日本語逐次音声合成における合成単位", 情報処理学会論文誌, Vol. 63, No. 4, pp. 1149-1158, Apr. 2022[PDF]
  2. B. Wu, S. Sakti, J. Zhang, S. Nakamura, "Modeling Unsupervised Empirical Adaptation by DPGMM and DPGMM-RNN Hybrid Model to Extract Perceptual Features for Low-Resource ASR", IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), Vol. 30, pp. 901-916, Feb 2022 [PDF]
  3. S. Novitasari, S. Sakti, S. Nakamura, "Neural Incremental Speech Recognition Toward Real-Time Machine Speech Translation", IEICE Transactions on Information and Systems, E104.D (12), pp. 2195-2208, Dec 2021 [PDF]