Boris Ginsburg

4.5k total citations
68 papers, 972 citations indexed

About

Boris Ginsburg is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, Boris Ginsburg has authored 68 papers receiving a total of 972 indexed citations (citations by other indexed papers that have themselves been cited), including 60 papers in Artificial Intelligence, 30 papers in Signal Processing and 4 papers in Computer Vision and Pattern Recognition. Recurrent topics in Boris Ginsburg's work include Speech Recognition and Synthesis (50 papers), Natural Language Processing Techniques (25 papers) and Speech and Audio Processing (23 papers). Boris Ginsburg is often cited by papers focused on Speech Recognition and Synthesis (50 papers), Natural Language Processing Techniques (25 papers) and Speech and Audio Processing (23 papers). Boris Ginsburg collaborates with scholars based in United States, United Kingdom and Russia. Boris Ginsburg's co-authors include Vitaly Lavrukhin, Oleksii Kuchaiev, Somshubra Majumdar, Jason Li, R. Bret Leary, Stanislav Beliaev, Samuel Kriman, Jocelyn Huang, Taejin Park and Yang Zhang and has published in prestigious journals such as Journal of Chemical Information and Modeling, Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization and arXiv (Cornell University).

In The Last Decade

Boris Ginsburg

57 papers receiving 894 citations

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Boris Ginsburg United States 13 678 391 154 85 50 68 972
Kartik Audhkhasi United States 19 812 1.2× 458 1.2× 106 0.7× 40 0.5× 65 1.1k
Francisco de Assis Brazil 11 146 0.2× 45 0.1× 57 0.4× 16 0.2× 3 0.1× 110 510
Abhinav Sethy United States 23 1.2k 1.8× 637 1.6× 104 0.7× 12 0.1× 73 1.4k
Petros Elia France 19 293 0.4× 192 0.5× 248 1.6× 18 0.2× 92 1.5k
Mikio L. Braun Germany 9 314 0.5× 95 0.2× 130 0.8× 9 0.1× 16 597
Yuanhua Qiao China 16 157 0.2× 53 0.1× 109 0.7× 114 1.3× 86 712
H.-U. Bauer Germany 13 397 0.6× 94 0.2× 188 1.2× 3 0.0× 2 0.0× 25 715
Malte Kuß Germany 9 302 0.4× 41 0.1× 56 0.4× 7 0.1× 2 0.0× 11 532
Johannes Fischer Germany 11 287 0.4× 74 0.2× 79 0.5× 28 0.3× 55 549
Masato Mimura Japan 14 401 0.6× 301 0.8× 39 0.3× 26 0.3× 1 0.0× 69 629

Countries citing papers authored by Boris Ginsburg

Since Specialization
Citations

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

Fields of papers citing papers by Boris Ginsburg

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Boris Ginsburg

This figure shows the co-authorship network connecting the top 25 collaborators of Boris Ginsburg. A scholar is included among the top collaborators of Boris Ginsburg 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 Boris Ginsburg. Boris Ginsburg 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
1.
Żelasko, Piotr, Zhehuai Chen, Daniel Gálvez, et al.. (2025). EMMeTT: Efficient Multimodal Machine Translation Training. 1–5. 1 indexed citations
2.
3.
Ghosh, Subhankar, et al.. (2024). Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment. 3425–3429. 1 indexed citations
4.
Kriman, Samuel, et al.. (2024). Investigating End-to-End ASR Architectures for Long Form Audio Transcription. 13366–13370. 1 indexed citations
5.
Chen, Zhehuai, et al.. (2024). Bestow: Efficient and Streamable Speech Language Model with The Best of Two Worlds in GPT and T5. 147–154. 2 indexed citations
6.
7.
Park, Tae‐Jin, et al.. (2023). The CHiME-7 Challenge: System Description and Performance of NeMo Team’s DASR System. 57–62. 4 indexed citations
8.
H, Xu, et al.. (2023). Multi-Blank Transducers for Speech Recognition. 28. 1–5. 3 indexed citations
9.
Hrinchuk, Oleksii, et al.. (2023). NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2023. 442–448.
10.
Батаев, В. А., et al.. (2023). Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator. 2928–2932. 5 indexed citations
11.
12.
Lavrukhin, Vitaly, Somshubra Majumdar, Vahid Noroozi, et al.. (2021). SPGISpeech: 5,000 Hours of Transcribed Financial Audio for Fully Formatted End-to-End Speech Recognition. 1434–1438. 20 indexed citations
13.
Kriman, Samuel, Stanislav Beliaev, Boris Ginsburg, et al.. (2020). Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions. 6124–6128. 149 indexed citations
14.
Majumdar, Somshubra & Boris Ginsburg. (2020). MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition. arXiv (Cornell University). 57 indexed citations
15.
Li, Jason, Vitaly Lavrukhin, Boris Ginsburg, et al.. (2019). Jasper: An End-to-End Convolutional Neural Acoustic Model. 71–75. 117 indexed citations
16.
Ginsburg, Boris, Patrice Castonguay, Oleksii Hrinchuk, et al.. (2019). Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments. 2 indexed citations
17.
Jin, Peter, Boris Ginsburg, & Kurt Keutzer. (2018). Spatially Parallel Convolutions.. International Conference on Learning Representations. 3 indexed citations
18.
Micikevicius, Paulius, Sharan Narang, Gregory Diamos, et al.. (2017). Mixed Precision Training. arXiv (Cornell University). 62 indexed citations
19.
Kuchaiev, Oleksii & Boris Ginsburg. (2017). Factorization tricks for LSTM networks. International Conference on Learning Representations. 9 indexed citations
20.
Frumkin, Michael, et al.. (2017). On Improving the Numerical Stability of Winograd Convolutions. International Conference on Learning Representations. 12 indexed citations

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

Breakdown of academic impact, for papers by Kartik Audhkhasi Breakdown of academic impact, for papers by Francisco de Assis Breakdown of academic impact, for papers by Abhinav Sethy Breakdown of academic impact, for papers by Petros Elia Breakdown of academic impact, for papers by Mikio L. Braun Breakdown of academic impact, for papers by Yuanhua Qiao Breakdown of academic impact, for papers by H.-U. Bauer Breakdown of academic impact, for papers by Malte Kuß Breakdown of academic impact, for papers by Johannes Fischer Breakdown of academic impact, for papers by Masato Mimura
Rankless by CCL
2026