Martin Karafiát

77 papers receiving 5.3k citations

Hit Papers

Recurrent neural network based language model2010202620152020201010002.0k3.0k

Peers

Martin Karafiát
Comparison fields: 5 of 161
  • Artificial Intelligence 4.7k
  • Signal Processing 2.3k
  • Computer Vision and Pattern Recognition 918
  • Information Systems 412
  • Electrical and Electronic Engineering 212
Replace Jaň Černocký with:
Jaň Černocký Czechia
Bo Xu China
Lukáš Burget Czechia
Haşim Sak United States
Anthony G. Cohn United Kingdom
Michael Auli United States
Thang Luong United States
Ralf Schlüter Germany
Hieu Pham United States
David Grangier United States
Martin Karafiát relative to Jaň Černocký Czechia Jaň Černocký's profile →
Citations per field
00.5×1.5×
Jaň Černocký · 1×
Citations per year

Countries citing papers authored by Martin Karafiát

Since Specialization
Citations

This map shows the geographic impact of Martin Karafiát's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Martin Karafiát with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Martin Karafiát more than expected).

Fields of papers citing papers by Martin Karafiát

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Martin Karafiát. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Martin Karafiát. The network helps show where Martin Karafiát may publish in the future.

Co-authorship network of co-authors of Martin Karafiát

This figure shows the co-authorship network connecting the top 25 collaborators of Martin Karafiát. A scholar is included among the top collaborators of Martin Karafiát based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Martin Karafiát. Martin Karafiát is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
#WorkIndexed citations
1 1
2 1
3 4
4 6
5 11
6 1
7 8
8 11
9 20
10 18
11 77
12
Speaker vectors from subspace Gaussian mixture model as complementary features for language identification.
4
13 8
14 135
15 63
16
Data selection and calibration issues in automatic language recognition - investigation with BUT-AGNITIO NIST LRE 2009 system.
21
17 10
18 6
19 16
20
Proceedings of the 9th European Conference on Speech Communication and Technology
37

About Martin Karafiát

Martin Karafiát is a scholar working on Signal Processing, Artificial Intelligence and Hardware and Architecture, having authored 77 papers that have together received 5.9k indexed citations. Recurring topics across this work include Speech Recognition and Synthesis (64 papers), Speech and Audio Processing (34 papers) and Natural Language Processing Techniques (28 papers). The work is most often cited by research in Signal Processing (2.3k citations), Artificial Intelligence (4.7k citations) and Computer Vision and Pattern Recognition (918 citations). Martin Karafiát has collaborated with scholars based in Czechia, United States and Canada. Frequent co-authors include Lukáš Burget, Jaň Černocký, Tomáš Mikolov, Sanjeev Khudanpur, František Grézl, Karel Veselý, Ondřej Glembek, Petr Schwarz, Pavel Matějka and Stefan Kombrink. Their work appears in journals such as IEEE Transactions on Audio Speech and Language Processing, Computer Speech & Language and International Journal of Speech Technology.

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026