David Harwath
David Harwath
MIT Computer Science and Artificial Intelligence Laboratory
Потвърден имейл адрес: mit.edu
Заглавие
Позовавания
Позовавания
Година
Unsupervised learning of spoken language with visual context
D Harwath, A Torralba, J Glass
Advances in Neural Information Processing Systems, 1858-1866, 2016
159*2016
A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition
A Jansen, E Dupoux, S Goldwater, M Johnson, S Khudanpur, K Church, ...
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
932013
Deep multimodal semantic embeddings for speech and images
D Harwath, J Glass
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
692015
Jointly discovering visual objects and spoken words from raw sensory input
D Harwath, A Recasens, D Surís, G Chuang, A Torralba, J Glass
Proceedings of the European conference on computer vision (ECCV), 649-665, 2018
652018
Learning word-like units from joint audio-visual analysis
D Harwath, JR Glass
arXiv preprint arXiv:1701.07481, 2017
652017
Zero resource spoken audio corpus analysis
DF Harwath, TJ Hazen, JR Glass
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
292013
Vision as an interlingua: Learning multilingual semantic embeddings of untranscribed speech
D Harwath, G Chuang, J Glass
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
232018
Topic identification based extrinsic evaluation of summarization techniques applied to conversational speech
D Harwath, TJ Hazen
2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012
202012
Look, Listen, and Decode: Multimodal Speech Recognition with Images
F Sun, D Harwath, J Glass
IEEE Workshop on Spoken Language Technology, 2016
182016
Learning modality-invariant representations for speech and images
K Leidal, D Harwath, J Glass
2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2017
132017
Speech recognition without a lexicon—bridging the gap between graphemic and phonetic systems
D Harwath, JR Glass
Fifteenth Annual Conference of the International Speech Communication …, 2014
122014
Towards visually grounded sub-word speech unit discovery
D Harwath, J Glass
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
112019
Learning hierarchical discrete linguistic units from visually-grounded speech
D Harwath, WN Hsu, J Glass
arXiv preprint arXiv:1911.09602, 2019
92019
On the use of acoustic unit discovery for language recognition
SH Shum, DF Harwath, N Dehak, JR Glass
IEEE/ACM Transactions on Audio, Speech, and Language Processing 24 (9), 1665 …, 2016
92016
Choosing useful word alternates for automatic speech recognition correction interfaces
D Harwath, A Gruenstein, I McGraw
Fifteenth Annual Conference of the International Speech Communication …, 2014
72014
Transfer learning from audio-visual grounding to speech recognition
WN Hsu, D Harwath, J Glass
arXiv preprint arXiv:1907.04355, 2019
62019
Towards Bilingual Lexicon Discovery From Visually Grounded Speech Audio.
E Azuh, D Harwath, JR Glass
INTERSPEECH, 276-280, 2019
32019
Learning words by drawing images
D Suris, A Recasens, D Bau, D Harwath, J Glass, A Torralba
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019
32019
画像を説明する多言語音声データを利用したクロスモーダル探索
大石康智, 木村昭悟, 川西隆仁, 柏野邦夫, D Harwath, J Glass
信学技報 119 (64), 283-288, 2019
22019
Unsupervised modeling of latent topics and lexical units in speech audio
DF Harwath
Massachusetts Institute of Technology, 2013
22013
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20