Shankar Kumar

3.3k citations
30 papers · 1.8k indexed · 1 hit paper · h-index 18

Shankar Kumar

29 papers receiving 1.6k citations

Hit Papers

Transformer Transducer: A Streamable Speech Recognition M...277202020262022202450100150200250

Peers

Shankar Kumar
Comparison fields: 5 of 80
  • Artificial Intelligence 1.6k
  • Signal Processing 252
  • Information Systems 268
  • Computer Vision and Pattern Recognition 218
  • Statistical and Nonlinear Physics 55
Replace Douglass R. Cutting with:
Douglass R. Cutting United States
William M. Pottenger United States
Kuiyu Chang Singapore
Deepak Ravichandran United States
Qipeng Guo China
Maya Ramanath Germany
Mathias Niepert United States
Chinatsu Aone United States
Francis Kubala United States
Justin Betteridge United States
Shankar Kumar relative to Douglass R. Cutting United States Douglass R. Cutting's profile →
Citations per field
00.5×10×20×30×36×
Douglass R. Cutting · 1×
Citations per year

Countries citing papers authored by Shankar Kumar

Since Specialization
Citations

This map shows the geographic impact of Shankar Kumar'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 Shankar Kumar with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Shankar Kumar more than expected).

Fields of papers citing papers by Shankar Kumar

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Shankar Kumar. 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 Shankar Kumar. The network helps show where Shankar Kumar may publish in the future.

Co-authorship network

The 25 scholars most cited alongside Shankar Kumar, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Shankar Kumar Line = papers co-authored together Shankar Kumar links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown
#Work
1 20240
2 20231
3
Data Strategies for Low-Resource Grammatical Error Correction
20219
4 20215
5
Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Lossbreakdown →
2020277
6 20182
7 20183
8 201547
9
Expected Sequence Similarity Maximization
20103
10
Model Combination for Machine Translation
201021
11 2008296
12 200888
13
Improving Word Alignment with Bridge Languages
200736
14 200625
15
Minimum bayes-risk techniques in automatic speech recognition and statistical machine translation
20053
16 200547
17 2004191
18 200346
19 200213
20 200020

About Shankar Kumar

Shankar Kumar is a scholar working on Artificial Intelligence, Signal Processing, Computer Vision and Pattern Recognition, Computational Theory and Mathematics and Information Systems, having authored 30 papers that have together received 1.8k indexed citations. Recurring topics across this work include Topic Modeling (23 papers), Natural Language Processing Techniques (22 papers), Speech Recognition and Synthesis (9 papers), Text Readability and Simplification (7 papers), Algorithms and Data Compression (6 papers), Speech and dialogue systems (3 papers), Speech and Audio Processing (2 papers) and Music and Audio Processing (2 papers). The work is most often cited by research in Artificial Intelligence (1.6k citations), Signal Processing (252 citations), Information Systems (268 citations), Computer Vision and Pattern Recognition (218 citations) and Statistical and Nonlinear Physics (55 citations). Shankar Kumar has collaborated with scholars based in United States, United Kingdom and India. Frequent co-authors include Bill Byrne, Franz Josef Och, Wolfgang Macherey, Qian Zhang, Erik McDermott, Haşim Sak, Anshuman Tripathi, Lu Han, Mohamed Aly and Richard Sproat. Their work appears in journals such as Natural Language Engineering, Tetrahedron Letters, Computer Speech & Language, Empirical Methods in Natural Language Processing and North American Chapter of the Association for Computational Linguistics.

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