Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Gabriel Synnaeve"'
Autor:
Gabriel Synnaeve, Pierre Bessière
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. 8:25-30
This paper advocates the exploration of the full state of recorded real-time strategy (RTS) games, by human or robotic players, to discover how to reason about tactics and strategy. We present a dataset of StarCraft games encompassing the most of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4cf4ae86fa03d4bd23a05f88b466ebfa
https://doi.org/10.1609/aiide.v8i3.12546
https://doi.org/10.1609/aiide.v8i3.12546
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment. 13:8-14
Real-Time Strategy games have become a popular test-bed for modern AI system due to their real-time computational constraints, complex multi-unit control problems, and imperfect information. One of the most important aspects of any RTS AI system is t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::43ade79fe5c59142f94ace949fffee4d
https://doi.org/10.1609/aiide.v13i2.12962
https://doi.org/10.1609/aiide.v13i2.12962
In this paper, we study training of automatic speech recognition system in a weakly supervised setting where the order of words in transcript labels of the audio training data is not known. We train a word-level acoustic model which aggregates the di
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33f3599023480c64f7a523b9cb6b2442
http://arxiv.org/abs/2110.05994
http://arxiv.org/abs/2110.05994
Autor:
Vineel Pratap, Michael Auli, Ann B. Lee, Tatiana Likhomanenko, Gabriel Synnaeve, Alexei Baevski, Ronan Collobert, Anuroop Sriram, Qiantong Xu, Jacob Kahn, Wei-Ning Hsu
Publikováno v:
Interspeech 2021.
Self-supervised learning of speech representations has been a very active research area but most work is focused on a single domain such as read audio books for which there exist large quantities of labeled and unlabeled data. In this paper, we explo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c73d193fc72ccadb64227828a5d482e
https://doi.org/10.21437/interspeech.2021-236
https://doi.org/10.21437/interspeech.2021-236
Autor:
Michael Auli, Alexis Conneau, Tatiana Likhomanenko, Qiantong Xu, Paden Tomasello, Gabriel Synnaeve, Alexei Baevski, Ronan Collobert
Publikováno v:
ICASSP
Self-training and unsupervised pre-training have emerged as effective approaches to improve speech recognition systems using unlabeled data. However, it is not clear whether they learn similar patterns or if they can be effectively combined. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2cbaeb347dc71d642bd291b9b8e4712c
https://doi.org/10.1109/icassp39728.2021.9414641
https://doi.org/10.1109/icassp39728.2021.9414641
Publikováno v:
ICASSP
Self-supervised learning (SSL) has shown promise in learning representations of audio that are useful for automatic speech recognition (ASR). But, training SSL models like wav2vec~2.0 requires a two-stage pipeline. In this paper we demonstrate a sing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b0adc9e831ee345d8e3c698df1e510d1
https://doi.org/10.1109/icassp39728.2021.9414227
https://doi.org/10.1109/icassp39728.2021.9414227
Publikováno v:
SLT
For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by assigning them low probability. In this work, we propose local prior
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4503ed326645b0caf740eac3ebf3d249
https://doi.org/10.1109/slt48900.2021.9383552
https://doi.org/10.1109/slt48900.2021.9383552
Autor:
Hugo Touvron, Piotr Bojanowski, Mathilde Caron, Matthieu Cord, Alaaeldin El-Nouby, Edouard Grave, Gautier Izacard, Armand Joulin, Gabriel Synnaeve, Jakob Verbeek, Herve Jegou
We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which image patches interact, independently and identically across channels
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d039734818b3004f9b4785d6ef946728
Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so far. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8bd98a83cf9687506a2d7921a40b794f
Autor:
Morgane Riviere, Eugene Kharitonov, Gabriel Synnaeve, Pierre-Emmanuel Mazaré, Lior Wolf, Matthijs Douze, Emmanuel Dupoux
Publikováno v:
SLT 2020-IEEE Spoken Language Technology Workshop
SLT 2020-IEEE Spoken Language Technology Workshop, Dec 2020, Shenzhen / Virtual, China
SLT
HAL
SLT 2020-IEEE Spoken Language Technology Workshop, Dec 2020, Shenzhen / Virtual, China
SLT
HAL
Contrastive Predictive Coding (CPC), based on predicting future segments of speech from past segments is emerging as a powerful algorithm for representation learning of speech signal. However, it still under-performs compared to other methods on unsu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41c7748fbee8fd180fd243940e22e72f
https://hal.science/hal-03070321
https://hal.science/hal-03070321