Science Explorer Back to mapMap
Discussion
Researcher · Brno University of Technology · Czechia

Martin Karafiát

Martin Karafiát publishes mostly in Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition, on topics such as Speech Recognition and Synthesis, Speech and Audio Processing and Natural Language Processing Techniques.

ORCID 0000-0001-6474-8366 OpenAlex
World rank
#203,276
of 7,710,434 ranked researchers
Rank in Czechia
#268
of 39,303
Works
108
Citations
9.4k
Citations per work
87.2
h-index
33
i10-index 61Top 3.7% in Artificial Intelligence
Martin Karafiát

What does Martin Karafiát research?

Martin Karafiát's work is mostly in Computer Science (94%), Psychology (1%), Engineering (1%).

Physical Sciences: 102 works · 94.8% of their workComputer Science: 102 works · 94.1% of their workArtificial Intelligence: 64 works · 59.6% of their workSignal Processing: 33 works · 30.6% of their workComputer Vision and Pattern Recognition: 3 works · 2.9% of their workHardware and Architecture: 1 works · 1.0% of their workEngineering: 1 works · 0.7% of their workComputational Mechanics: 1 works · 0.7% of their workEverything else: 5 works · 4.2% of their workSocial Sciences: 1 works · 1.0% of their workPsychology: 1 works · 1.0% of their workExperimental and Cognitive Psychology: 1 works · 1.0% of their workTHEIR WORKMartin Karafiát108works
Physical Sciences95%Social Sciences1%

Their six largest subfields, inside their fields and domains; the grey slice is everything else they publish. The interactive view splits every one of their works down to single topics.

The fields and subfields, with their numbers
    1. Computer Science10294.1%
    2. Engineering10.7%
  2. Everything else54.2%
    1. Psychology11.0%
  1. 1Artificial Intelligence60% of their works
  2. 2Signal Processing31% of their works
  3. 3Computer Vision and Pattern Recognition3% of their works
  4. 4Hardware and Architecture1% of their works
  5. 5Experimental and Cognitive Psychology1% of their works
  6. 6Computational Mechanics1% of their works

Research topics

Which keywords describe Martin Karafiát's research?

The keywords of their largest research topics: Convolutional Neural Networks, Deep Learning, Acoustic Modeling, Deep Neural Networks, Neural Networks, Audio-Visual Speech Recognition, Speech Enhancement and Neural Machine Translation.

Size is their works in the topics tagged with each word, from their 8 largest topics. Each links to the topic it comes from most.

All 19 words, with their numbers
  1. Convolutional Neural Networks1302 topics
  2. Deep Learning983 topics
  3. Acoustic Modeling921 topic
  4. Deep Neural Networks921 topic
  5. Neural Networks733 topics
  6. Audio-Visual Speech Recognition511 topic
  7. Speech Enhancement511 topic
  8. Neural Machine Translation401 topic
  9. Statistical Machine Translation401 topic
  10. Audio Signal Classification381 topic
  11. Music Information Retrieval381 topic
  12. Markov Decision Processes171 topic
  13. Spoken Dialogue Systems171 topic
  14. Machine Translation131 topic
  15. Word Representation131 topic
  16. Backpropagation Learning91 topic
  17. Self-Organizing Maps91 topic
  18. Compression41 topic
  19. Suffix Arrays41 topic

Where does Martin Karafiát work?

Martin Karafiát's main affiliation in the publication record is Brno University of Technology, Czechia.

How many publications and citations does Martin Karafiát have?

OpenAlex counts 108 works and 9,416 citations for Martin Karafiát, an h-index of 33, ranking #203,276 of 7,710,434 researchers worldwide on the quality score.

Ranked on field-normalised excellence (50%), output (30%) and citations (20%). Counts come from OpenAlex author records, which occasionally merge different people who share a name or split one person into several.

Papers, co-authors, who cited this work and researchers on the nearest topics have tabs of their own, above. Is this your page? Claim it with your ORCID iD, or request a correction or removal.

Discussion

Ask a question or share a note about Martin Karafiát. Posts are plain text and can be reported.