Dmitriy Serdyuk
Impact in
- Signal Processing top 10%
- Speech and Audio Processing
- Music and Audio Processing
-
- Speech Recognition and Synthesis
- Topic Modeling
- Natural Language Processing Techniques
Papers in
-
- Music and Audio Processing 3
- Speech and Audio Processing 3
-
- Speech Recognition and Synthesis 2
- Natural Language Processing Techniques 1
- Topic Modeling 1
- Machine Learning in Healthcare 1
- Co-authors
- Olivier Siohan (4 shared papers)Alessandro Sordoni (2 shared papers)Nan Rosemary Ke (2 shared papers)Chris Pal (2 shared papers)Yoshua Bengio (3 shared papers)Adam Trischler (1 shared paper)Hank Liao (1 shared paper)Oscar Chang (1 shared paper)
- Journals
- PolyPublie (École Polytechnique de Montréal) (1 paper)arXiv (Cornell University) (2 papers)Interspeech 2022 (1 paper)Zenodo (CERN European Organization for Nuclear Research) (1 paper)
- Partner nations
- United StatesCanadaGermany
In The Last Decade
Dmitriy Serdyuk
7 papers receiving 93 citations
Peers
Comparison fields: 5 of 15
- Signal Processing 68
- Artificial Intelligence 61
- Computer Vision and Pattern Recognition 25
- Experimental and Cognitive Psychology 4
- Music 1
Countries citing papers authored by Dmitriy Serdyuk
This map shows the geographic impact of Dmitriy Serdyuk'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 Dmitriy Serdyuk with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Dmitriy Serdyuk more than expected).
Fields of papers citing papers by Dmitriy Serdyuk
This network shows the impact of papers produced by Dmitriy Serdyuk. 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 Dmitriy Serdyuk. The network helps show where Dmitriy Serdyuk may publish in the future.
Co-authors
The 13 scholars most cited alongside Dmitriy Serdyuk, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | 2021 | 25 | |
| 2 | 2022 | 24 | |
| 3 | Twin Networks: Matching the Future for Sequence Generation | 2018 | 16 |
| 4 | 2024 | 16 | |
| 5 | Audio-Visual Speech Recognition is Worth 32×32×8 Voxels. | 2021 | 8 |
| 6 | Twin Networks: Using the Future as a Regularizer. | 2017 | 5 |
| 7 | 2015 | 3 | |
| 8 | 2024 | 0 |
About Dmitriy Serdyuk
Dmitriy Serdyuk is a scholar working on Signal Processing, Artificial Intelligence, Computer Vision and Pattern Recognition, Infectious Diseases and Organic Chemistry, having authored 8 papers that have together received 97 indexed citations. Recurring topics across this work include Music and Audio Processing (3 papers), Speech and Audio Processing (3 papers), Speech Recognition and Synthesis (2 papers), Advanced Data Compression Techniques (2 papers), Natural Language Processing Techniques (1 paper), Image and Signal Denoising Methods (1 paper), Topic Modeling (1 paper) and Machine Learning in Healthcare (1 paper). The work is most often cited by research in Signal Processing (68 citations), Artificial Intelligence (61 citations), Computer Vision and Pattern Recognition (25 citations), Experimental and Cognitive Psychology (4 citations) and Music (1 citation). Dmitriy Serdyuk has collaborated with scholars based in United States, Canada and Germany. Frequent co-authors include Olivier Siohan, Alessandro Sordoni, Nan Rosemary Ke, Chris Pal, Yoshua Bengio, Adam Trischler, Hank Liao, Oscar Chang, Bart van Merriënboer and Dmitry Bogdanov. Their work appears in journals such as PolyPublie (École Polytechnique de Montréal), arXiv (Cornell University), Interspeech 2022 and Zenodo (CERN European Organization for Nuclear Research).
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.