Mirco Ravanelli
Artificial Intelligence · 2012–2021
A researcher in the Science corpus: 21 papers; trusts 1,076 researchers and is trusted by 2,509 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 514 citations into it; #543 of 36,961 by trust here, #3,474 by citations
- Signal Processing — 320 citations into it; #306 of 7,592 by trust here, #285 by citations
- Speech & Audio — 253 citations into it; #121 of 1,080 by trust here, #152 by citations
- Model Architectures — 120 citations into it; #1,361 of 2,288 by trust here, #1,754 by citations
- Computer Vision and Pattern Recognition — 93 citations into it
- Natural Language Processing — 77 citations into it
- Optimization & Training — 69 citations into it; #2,441 of 2,605 by trust here, #2,316 by citations
- Evaluation & Benchmarks — 60 citations into it; #2,234 of 3,155 by trust here, #2,488 by citations
Whom Mirco Ravanelli trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Alex Graves
- Sergey Ioffe
- Diederik P. Kingma
- Xavier Glorot
- Alex Krizhevsky
- Maurizio Omologo
- Jimmy Ba
- Christian Szegedy
Who trusts Mirco Ravanelli overall
- Yoshua Bengio
- Santiago Pascual
- Titouan Parcollet
- Maurizio Omologo
- Philemon Brakel
- Alexei Baevski
- Sergey Levine
- Quoc V. Le
- Ruslan Salakhutdinov
- Hervé Bredin
Papers from Mirco Ravanelli's perspective
Ordered by how strongly the researchers Mirco Ravanelli trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
Their papers
- Multi-Task Self-Supervised Learning for Robust Speech Recognition (2020) — 310 citations
- Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks (2019) — 259 citations
- Speech Model Pre-training for End-to-End Spoken Language Understanding (2019) — 402 citations
- The DIRHA-ENGLISH corpus and related tasks for distant-speech recognition in domestic environments (2015) — 61 citations
- Light Gated Recurrent Units for Speech Recognition (2018) — 369 citations
- The Pytorch-kaldi Speech Recognition Toolkit (2018) — 241 citations
- Learning Speaker Representations with Mutual Information (2018) — 96 citations
- On the selection of the impulse responses for distant-speech recognition based on contaminated speech training (2014) — 25 citations
- Impulse response estimation for robust speech recognition in a reverberant environment (2012) — 32 citations
- Improving Speech Recognition by Revising Gated Recurrent Units (2017) — 56 citations
- Contaminated speech training methods for robust DNN-HMM distant speech recognition (2017) — 32 citations
- Batch-normalized joint training for DNN-based distant speech recognition (2016) — 35 citations
- A network of deep neural networks for Distant Speech Recognition (2017) — 41 citations
- Realistic Multi-Microphone Data Simulation for Distant Speech Recognition (2016) — 37 citations
- Quaternion Recurrent Neural Networks (2018) — 153 citations
- Speaker Recognition from Raw Waveform with SincNet (2018) — 875 citations
- Twin Regularization for online speech recognition (2018) — 16 citations
- SpeechBrain: A General-Purpose Speech Toolkit (2021) — 999 citations
- MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement (2021) — 305 citations
- Attention Is All You Need In Speech Separation (2020) — 785 citations