Michiel Bacchiani

Artificial Intelligence · 2003–2022

A researcher in the Science corpus: 13 papers; trusts 104 researchers and is trusted by 38 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 213 citations into it; #5,330 of 35,345 by trust here, #2,668 by citations
• Signal Processing — 184 citations into it; #1,409 of 7,572 by trust here, #299 by citations
• Speech & Audio — 104 citations into it; #409 of 1,076 by trust here, #149 by citations
• Natural Language Processing — 56 citations into it
• Computer Vision and Pattern Recognition — 50 citations into it
• Model Architectures — 41 citations into it
• Generative Models — 33 citations into it
• Optimization & Training — 22 citations into it

Whom Michiel Bacchiani trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Brian Roark
2. Tara N. Sainath
3. Michael Collins
4. Geoffrey E. Hinton
5. Alex Graves
6. Yoshua Bengio
7. Diederik P. Kingma
8. Daniel Gildea
9. Kaiming He
10. Alex Krizhevsky

Who trusts Michiel Bacchiani overall

1. Yishay Mansour
2. Lorenzo Bruzzone
3. Yulan He
4. Mehryar Mohri
5. Tara N. Sainath
6. John Blitzer
7. Jie Lu
8. Joakim Nivre
9. Bo Li
10. Ryan T. McDonald

Papers from Michiel Bacchiani's perspective

Ordered by how strongly the researchers Michiel Bacchiani trusts endorse each paper. Same corpus, a different order for every researcher.

1. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Long Short-Term Memory
4. ImageNet classification with deep convolutional neural networks
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
8. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
9. ImageNet: A large-scale hierarchical image database
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• State-of-the-Art Speech Recognition with Sequence-to-Sequence Models (2017) — 1,190 citations
• Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling (2019) — 215 citations
• Multi-Dialect Speech Recognition with a Single Sequence-to-Sequence Model (2017) — 140 citations
• Toward Domain-Invariant Speech Recognition via Large Scale Training (2018) — 114 citations
• Supervised and unsupervised PCFG adaptation to novel domains (2003) — 110 citations
• End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow (2017) — 28 citations
• Neural Network Adaptive Beamforming for Robust Multichannel Speech Recognition (2016) — 117 citations
• Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home (2017) — 247 citations
• Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition (2017) — 213 citations
• Wavefit: an Iterative and Non-Autoregressive Neural Vocoder Based on Fixed-Point Iteration (2022) — 37 citations
• SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping (2022) — 58 citations
• Speech Processing for Digital Home Assistants: Combining signal processing with deep-learning techniques (2019) — 152 citations
• Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition (2018) — 37 citations