Tomi H. Kinnunen
Signal Processing · 2005–2022
A researcher in the Science corpus: 15 papers; trusts 40 researchers and is trusted by 27 researchers here, as inferred from the citation graph.
Subfields
- Signal Processing — 128 citations into it; #845 of 7,572 by trust here, #501 by citations
- Artificial Intelligence — 122 citations into it; #5,945 of 35,345 by trust here, #5,317 by citations
- Speech & Audio — 73 citations into it
- Computer Vision and Pattern Recognition — 37 citations into it
- Natural Language Processing — 19 citations into it
- Probabilistic & Bayesian Methods — 7 citations into it
- Representation & Self-Supervised Learning — 7 citations into it
Whom Tomi H. Kinnunen trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Patrick Kenny
- Douglas A. Reynolds
- William M. Campbell
- John I. Makhoul
- Chris Leggetter
- Paul P. G. Boersma
- Thomas F. Quatieri
- Hynek Hermansky
- A. de Cheveigné
- Simon J. D. Prince
Who trusts Tomi H. Kinnunen overall
- Massimiliano Todisco
- Md. Sahidullah
- Xin Eric Wang
- Junichi Yamagishi
- Roberto B. Togneri
- Sina Hamidi Ghalehjegh
- Héctor Delgado
- Weicheng Cai
- Xuechen Liu
- Hirokazu Kameoka
Papers from Tomi H. Kinnunen's perspective
Ordered by how strongly the researchers Tomi H. Kinnunen 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
- Long Short-Term Memory
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- WaveNet: A Generative Model for Raw Audio
- Speaker Verification Using Adapted Gaussian Mixture Models
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper
Their papers
- Improving K-Means by Outlier Removal (2005) — 144 citations
- The NIST 2014 Speaker Recognition i-vector Machine Learning Challenge (2014) — 108 citations
- An overview of text-independent speaker recognition: From features to supervectors (2010) — 1,634 citations
- Non-parallel voice conversion using i-vector PLDA: towards unifying speaker verification and transformation (2017) — 72 citations
- The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods (2018) — 351 citations
- ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild (2022) — 398 citations
- ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan (2021) — 91 citations
- ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection (2021) — 541 citations
- ASVspoof 2019: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan ∗ (2021)
- ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech (2019) — 651 citations
- ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection (2019) — 822 citations
- The ASVspoof 2017 Challenge: Assessing the Limits of Replay Spoofing Attack Detection (2017) — 605 citations
- A comparison of features for synthetic speech detection (2015) — 434 citations
- Spoofing and countermeasures for speaker verification: A survey (2015) — 705 citations
- ASVspoof 2015: the first automatic speaker verification spoofing and countermeasures challenge (2015) — 594 citations