Pavel Matejka

Artificial Intelligence · 2004–2017

A researcher in the Science corpus: 5 papers; trusts 4 researchers and is trusted by 15 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 17 citations into it; #11,423 of 35,345 by trust here, #12,387 by citations
• Signal Processing — 13 citations into it; #2,329 of 7,572 by trust here, #2,052 by citations
• Speech & Audio — 11 citations into it; #470 of 1,076 by trust here, #654 by citations

Whom Pavel Matejka trusts overall

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

1. Patrick Kenny
2. David Talkin
3. Najim Dehak
4. Simon J. D. Prince
5. Kai-Fu Lee
6. Pedro A. Torres-Carrasquillo
7. Hynek Hermansky
8. Pierre Ouellet
9. Tanja Schultz
10. Daniel Povey

Who trusts Pavel Matejka overall

1. Mitchell McLaren
2. Frantisek Grézl
3. Daniel Garcia-Romero
4. Taira Tsuchiya
5. Ehud Ben-Reuven
6. Fred Richardson
7. Joon Son Chung
8. Andros Tjandra
9. David Snyder
10. Gianni Brauwers

Papers from Pavel Matejka's perspective

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

1. A Study of Interspeaker Variability in Speaker Verification (IEEE Transactions on Audio, Speech, and Language Processing)
2. Joint Factor Analysis of Speaker and Session Variability: Theory and Algorithms
3. Bayesian Speaker Verification with Heavy-Tailed Priors
4. Probabilistic Linear Discriminant Analysis for Inferences About Identity
5. RASTA processing of speech
6. Automatic language identification using deep neural networks
7. Multitask Learning
8. Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error
9. Speaker Verification Using Adapted Gaussian Mixture Models
10. fMPE: discriminatively trained features for speech recognition (Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.)

Their papers

• iVector-based discriminative adaptation for automatic speech recognition (2011) — 96 citations
• Neural Network Bottleneck Features for Language Identification (2014) — 142 citations
• Full-covariance UBM and heavy-tailed PLDA in i-vector speaker verification (2011) — 208 citations
• Towards Lower Error Rates in Phoneme Recognition (2004) — 141 citations
• Multilingually trained bottleneck features in spoken language recognition (2017) — 62 citations