Prati
Andros Tjandra
Andros Tjandra
Facebook AI (research scientist)
Potvrđena adresa e-pošte na fb.com
Naslov
Citirano
Citirano
Godina
Transformer-based acoustic modeling for hybrid speech recognition
Y Wang, A Mohamed, D Le, C Liu, A Xiao, J Mahadeokar, H Huang, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
1682020
Listening while speaking: Speech chain by deep learning
A Tjandra, S Sakti, S Nakamura
2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2017
1592017
Compressing recurrent neural network with tensor train
A Tjandra, S Sakti, S Nakamura
2017 International Joint Conference on Neural Networks (IJCNN), 4451-4458, 2017
1052017
XLS-R: Self-supervised cross-lingual speech representation learning at scale
A Babu, C Wang, A Tjandra, K Lakhotia, Q Xu, N Goyal, K Singh, ...
arXiv preprint arXiv:2111.09296, 2021
932021
Vqvae unsupervised unit discovery and multi-scale code2spec inverter for zerospeech challenge 2019
A Tjandra, B Sisman, M Zhang, S Sakti, H Li, S Nakamura
arXiv preprint arXiv:1905.11449, 2019
582019
Machine speech chain with one-shot speaker adaptation
A Tjandra, S Sakti, S Nakamura
arXiv preprint arXiv:1803.10525, 2018
572018
Combining depth image and skeleton data from Kinect for recognizing words in the sign system for Indonesian language (SIBI [Sistem Isyarat Bahasa Indonesia])
E Rakun, M Andriani, IW Wiprayoga, K Danniswara, A Tjandra
2013 International Conference on Advanced Computer Science and Information …, 2013
512013
Local monotonic attention mechanism for end-to-end speech and language processing
A Tjandra, S Sakti, S Nakamura
arXiv preprint arXiv:1705.08091, 2017
482017
Tensor decomposition for compressing recurrent neural network
A Tjandra, S Sakti, S Nakamura
2018 International Joint Conference on Neural Networks (IJCNN), 1-8, 2018
382018
End-to-end feedback loss in speech chain framework via straight-through estimator
A Tjandra, S Sakti, S Nakamura
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
332019
Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networks
A Tjandra, C Liu, F Zhang, X Zhang, Y Wang, G Synnaeve, S Nakamura, ...
arXiv preprint arXiv:1910.10324, 2019
302019
Transformer vq-vae for unsupervised unit discovery and speech synthesis: Zerospeech 2020 challenge
A Tjandra, S Sakti, S Nakamura
arXiv preprint arXiv:2005.11676, 2020
262020
Combination of two-dimensional cochleogram and spectrogram features for deep learning-based ASR
A Tjandra, S Sakti, G Neubig, T Toda, M Adriani, S Nakamura
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
262015
Speech-to-speech translation between untranscribed unknown languages
A Tjandra, S Sakti, S Nakamura
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019
252019
Attention-based wav2text with feature transfer learning
A Tjandra, S Sakti, S Nakamura
2017 IEEE automatic speech recognition and understanding workshop (ASRU …, 2017
252017
Machine speech chain
A Tjandra, S Sakti, S Nakamura
IEEE/ACM Transactions on Audio, Speech, and Language Processing 28, 976-989, 2020
242020
Speech chain for semi-supervised learning of japanese-english code-switching asr and tts
S Nakayama, A Tjandra, S Sakti, S Nakamura
2018 IEEE Spoken Language Technology Workshop (SLT), 182-189, 2018
242018
Sequence-to-sequence ASR optimization via reinforcement learning
A Tjandra, S Sakti, S Nakamura
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
242018
Gated recurrent neural tensor network
A Tjandra, S Sakti, R Manurung, M Adriani, S Nakamura
2016 International Joint Conference on Neural Networks (IJCNN), 448-455, 2016
212016
Improved language identification through cross-lingual self-supervised learning
A Tjandra, DG Choudhury, F Zhang, K Singh, A Conneau, A Baevski, ...
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
172022
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20