Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Sakriani Sakti

Simultaneous Speech-to-Speech Translation System with Neural Incremental ASR, MT, and TTS


Nov 11, 2020
Katsuhito Sudoh, Takatomo Kano, Sashi Novitasari, Tomoya Yanagita, Sakriani Sakti, Satoshi Nakamura

* 6 pages 

  Access Paper or Ask Questions

Cross-Lingual Machine Speech Chain for Javanese, Sundanese, Balinese, and Bataks Speech Recognition and Synthesis


Nov 04, 2020
Sashi Novitasari, Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Accepted in SLTU-CCURL 2020 

  Access Paper or Ask Questions

Sequence-to-Sequence Learning via Attention Transfer for Incremental Speech Recognition


Nov 04, 2020
Sashi Novitasari, Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Accepted in INTERSPEECH 2019 

  Access Paper or Ask Questions

Incremental Machine Speech Chain Towards Enabling Listening while Speaking in Real-time


Nov 04, 2020
Sashi Novitasari, Andros Tjandra, Tomoya Yanagita, Sakriani Sakti, Satoshi Nakamura

* Accepted in INTERSPEECH 2020 

  Access Paper or Ask Questions

Augmenting Images for ASR and TTS through Single-loop and Dual-loop Multimodal Chain Framework


Nov 04, 2020
Johanes Effendi, Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Accepted at INTERSPEECH 2020 

  Access Paper or Ask Questions

The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units


Oct 12, 2020
Ewan Dunbar, Julien Karadayi, Mathieu Bernard, Xuan-Nga Cao, Robin Algayres, Lucas Ondel, Laurent Besacier, Sakriani Sakti, Emmanuel Dupoux

* Proceedings of Interspeech 2020 

  Access Paper or Ask Questions

ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation


Jul 08, 2020
Fan Yang, Xin Chang, Chenyu Dang, Ziqiang Zheng, Sakriani Sakti, Satoshi Nakamura, Yang Wu

* 4 pages 

  Access Paper or Ask Questions

Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge


May 24, 2020
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Submitted to INTERSPEECH 2020 

  Access Paper or Ask Questions

Using panoramic videos for multi-person localization and tracking in a 3D panoramic coordinate


Dec 05, 2019
Fan Yang, Feiran Li, Yang Wu, Sakriani Sakti, Satoshi Nakamura

* 5 pages 

  Access Paper or Ask Questions

Speech-to-speech Translation between Untranscribed Unknown Languages


Oct 05, 2019
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Accepted in IEEE ASRU 2019. Web-page for more samples & details: https://sp2code-translation-v1.netlify.com/ 

  Access Paper or Ask Questions

Make Skeleton-based Action Recognition Model Smaller, Faster and Better


Jul 29, 2019
Fan Yang, Sakriani Sakti, Yang Wu, Satoshi Nakamura

* 6 pages, 5 figures 

  Access Paper or Ask Questions

From Speech Chain to Multimodal Chain: Leveraging Cross-modal Data Augmentation for Semi-supervised Learning


Jun 03, 2019
Johanes Effendi, Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Submitted to INTERSPEECH 2019 

  Access Paper or Ask Questions

VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019


May 29, 2019
Andros Tjandra, Berrak Sisman, Mingyang Zhang, Sakriani Sakti, Haizhou Li, Satoshi Nakamura

* Submitted to Interspeech 2019 

  Access Paper or Ask Questions

The Zero Resource Speech Challenge 2019: TTS without T


Apr 25, 2019
Ewan Dunbar, Robin Algayres, Julien Karadayi, Mathieu Bernard, Juan Benjumea, Xuan-Nga Cao, Lucie Miskic, Charlotte Dugrain, Lucas Ondel, Alan W. Black, Laurent Besacier, Sakriani Sakti, Emmanuel Dupoux

* Interspeech 2019 

  Access Paper or Ask Questions

End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator


Oct 31, 2018
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura


  Access Paper or Ask Questions

Multi-scale Alignment and Contextual History for Attention Mechanism in Sequence-to-sequence Model


Jul 22, 2018
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura


  Access Paper or Ask Questions

Tensor Decomposition for Compressing Recurrent Neural Network


May 08, 2018
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Accepted at IJCNN 2018. Source code URL: https://github.com/androstj/tensor_rnn 

  Access Paper or Ask Questions

Machine Speech Chain with One-shot Speaker Adaptation


Mar 28, 2018
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura


  Access Paper or Ask Questions

Sequence-to-Sequence ASR Optimization via Reinforcement Learning


Feb 28, 2018
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Accepted at ICASSP 2018 

  Access Paper or Ask Questions

Interactive Image Manipulation with Natural Language Instruction Commands


Feb 23, 2018
Seitaro Shinagawa, Koichiro Yoshino, Sakriani Sakti, Yu Suzuki, Satoshi Nakamura

* accepted at NIPS 2017 ViGIL workshop (https://nips2017vigil.github.io/

  Access Paper or Ask Questions

Structured-based Curriculum Learning for End-to-end English-Japanese Speech Translation


Feb 13, 2018
Takatomo Kano, Sakriani Sakti, Satoshi Nakamura


  Access Paper or Ask Questions

Local Monotonic Attention Mechanism for End-to-End Speech and Language Processing


Nov 03, 2017
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Accepted at IJCNLP 2017 --- (V2: added more experiments on G2P & MT) 

  Access Paper or Ask Questions

Attention-based Wav2Text with Feature Transfer Learning


Sep 22, 2017
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Accepted at ASRU 2017 

  Access Paper or Ask Questions

Listening while Speaking: Speech Chain by Deep Learning


Jul 16, 2017
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura


  Access Paper or Ask Questions

Gated Recurrent Neural Tensor Network


Jun 07, 2017
Andros Tjandra, Sakriani Sakti, Ruli Manurung, Mirna Adriani, Satoshi Nakamura

* Accepted at IJCNN 2016 URL : http://ieeexplore.ieee.org/document/7727233/ 

  Access Paper or Ask Questions

Compressing Recurrent Neural Network with Tensor Train


May 23, 2017
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

* Accepted at IJCNN 2017 

  Access Paper or Ask Questions