Martti Vainio

Artificial Intelligence · 2017–2023

A researcher in the Science corpus: 3 papers; trusts 6 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 18 citations into it
• Natural Language Processing — 6 citations into it
• Signal Processing — 6 citations into it

Whom Martti Vainio trusts overall

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

1. Adrian La'ncucki
2. Stéphane Mallat
3. Jacob Devlin

Papers from Martti Vainio's perspective

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

1. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
2. Language Models are Unsupervised Multitask Learners
3. Efficient Estimation of Word Representations in Vector Space
4. GloVe: Global Vectors for Word Representation
5. Attention is All you Need (Neural Information Processing Systems)
6. ImageNet classification with deep convolutional neural networks
7. Librispeech: An ASR corpus based on public domain audio books
8. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
9. Long Short-Term Memory
10. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)

Their papers

• Investigating the Utility of Surprisal from Large Language Models for Speech Synthesis Prosody (2023) — 6 citations
• Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations (2019) — 31 citations
• Hierarchical representation and estimation of prosody using continuous wavelet transform (2017) — 85 citations