Takafumi Koshinaka

Artificial Intelligence · 2018

A researcher in the Science corpus: 1 paper; trusts 18 researchers and is trusted by 16 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 15 citations into it; #10,572 of 35,345 by trust here, #21,316 by citations
• Signal Processing — 11 citations into it; #1,900 of 7,572 by trust here, #3,913 by citations
• Speech & Audio — 8 citations into it
• Computer Vision and Pattern Recognition — 5 citations into it

Whom Takafumi Koshinaka trusts overall

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

1. Sergey Ioffe
2. Daniel Garcia-Romero
3. Yun Lei
4. David Snyder
5. Simon J. D. Prince
6. Mitchell McLaren
7. Arsha Nagrani
8. Gautam Bhattacharya
9. Georg Heigold
10. Daniel Povey

Who trusts Takafumi Koshinaka overall

1. Jee-weon Jung
2. Joon Son Chung
3. Hee-Soo Heo
4. Arsha Nagrani
5. Zhongxin Bai
6. Weidi Xie
7. Brecht Desplanques
8. Hyeong-Seok Choi
9. Hemlata Tak
10. Jenthe Thienpondt

Papers from Takafumi Koshinaka's perspective

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

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Front-End Factor Analysis for Speaker Verification
4. The Kaldi Speech Recognition Toolkit
5. Attention is All you Need (Neural Information Processing Systems)
6. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
7. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
8. Front-End Factor Analysis For Speaker Verification
9. Long Short-Term Memory
10. Gradient-based learning applied to document recognition

Their papers

• Attentive Statistics Pooling for Deep Speaker Embedding (2018) — 633 citations