Jay Mahadeokar

866 total citations
28 papers, 372 citations indexed

About

Jay Mahadeokar is a scholar working on Artificial Intelligence, Signal Processing and Computational Theory and Mathematics. According to data from OpenAlex, Jay Mahadeokar has authored 28 papers receiving a total of 372 indexed citations (citations by other indexed papers that have themselves been cited), including 24 papers in Artificial Intelligence, 11 papers in Signal Processing and 2 papers in Computational Theory and Mathematics. Recurrent topics in Jay Mahadeokar's work include Speech Recognition and Synthesis (21 papers), Speech and Audio Processing (10 papers) and Natural Language Processing Techniques (9 papers). Jay Mahadeokar is often cited by papers focused on Speech Recognition and Synthesis (21 papers), Speech and Audio Processing (10 papers) and Natural Language Processing Techniques (9 papers). Jay Mahadeokar collaborates with scholars based in United States, India and Israel. Jay Mahadeokar's co-authors include Christian Fuegen, Michael L. Seltzer, Duc Le, Yuan Shangguan, Ozlem Kalinli, Alex Xiao, Chunxi Liu, Frank Zhang, Abdelrahman Mohamed and Yongqiang Wang and has published in prestigious journals such as Journal of Combinatorial Optimization, Journal of Discrete Algorithms and Infoscience (Ecole Polytechnique Fédérale de Lausanne).

In The Last Decade

Jay Mahadeokar

24 papers receiving 323 citations

Peers — A (Enhanced Table)

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

Name	h						Papers	Cites
Jay Mahadeokar United States	8	324	201	23	11	11	28	372
Zhongxin Bai China	6	254 0.8×	219 1.1×	39 1.7×	17 1.5×	9 0.8×	10	320
Vitaly Lavrukhin United States	6	312 1.0×	214 1.1×	44 1.9×	13 1.2×	15 1.4×	20	371
Matt Shannon United Kingdom	11	317 1.0×	250 1.2×	26 1.1×	5 0.5×	16 1.5×	13	372
Mike Seltzer United States	7	265 0.8×	196 1.0×	45 2.0×	6 0.5×	5 0.5×	17	311
Vineel Pratap United States	7	253 0.8×	123 0.6×	33 1.4×	10 0.9×	17 1.5×	16	311
Soyeon Choe South Korea	6	263 0.8×	263 1.3×	32 1.4×	5 0.5×	5 0.5×	8	323
Yatharth Saraf United States	9	385 1.2×	225 1.1×	57 2.5×	8 0.7×	23 2.1×	17	459
Franco Mana Italy	10	369 1.1×	285 1.4×	40 1.7×	9 0.8×	15 1.4×	41	419
Zhendong Peng China	8	269 0.8×	197 1.0×	29 1.3×	11 1.0×	16 1.5×	13	326

Countries citing papers authored by Jay Mahadeokar

Since Specialization

Citations

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

Fields of papers citing papers by Jay Mahadeokar

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Jay Mahadeokar

This figure shows the co-authorship network connecting the top 25 collaborators of Jay Mahadeokar. A scholar is included among the top collaborators of Jay Mahadeokar 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 Jay Mahadeokar. Jay Mahadeokar is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

Raj, Desh, Gil Keren, Junteng Jia, Jay Mahadeokar, & Ozlem Kalinli. (2025). Faster Speech-LLaMA Inference with Multi-token Prediction. 1–5.

Zhou, Wei, Junteng Jia, Leda Sarı, Jay Mahadeokar, & Ozlem Kalinli. (2025). CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR. 1–5. 1 indexed citations

Jia, Junteng, Chunyang Wu, Wei Zhou, et al.. (2025). Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech. 4323–4327. 1 indexed citations

Wu, Chunyang, Ke Li, Junteng Jia, et al.. (2024). AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs. 5522–5532. 6 indexed citations

Shangguan, Yuan, Haichuan Yang, Danni Li, et al.. (2024). TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-Device ASR Models. 10216–10220.

Wu, Chunyang, Junteng Jia, Yuan Shangguan, et al.. (2024). Prompting Large Language Models with Speech Recognition Abilities. 13351–13355. 40 indexed citations

Guo, Jinxi, Niko Moritz, Frank Seide, et al.. (2024). Effective Internal Language Model Training and Fusion for Factorized Transducer Model. 12687–12691. 1 indexed citations

Guo, Jinxi, Andros Tjandra, Yuan Shangguan, et al.. (2024). Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of a Multilingual ASR Model. 12201–12205. 1 indexed citations

Li, Ke, Jay Mahadeokar, Jinxi Guo, et al.. (2023). Improving fast-slow Encoder based Transducer with Streaming Deliberation. 1–5. 3 indexed citations

10.

Moritz, Niko, Frank Seide, Duc Le, Jay Mahadeokar, & Christian Fuegen. (2023). An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition. 324–330. 5 indexed citations

11.

Liang, Dawei, Hang Su, T. P. Singh, et al.. (2023). Dynamic Speech Endpoint Detection with Regression Targets. 1–5.

12.

Jia, Junteng, et al.. (2023). Joint Federated Learning and Personalization for on-Device ASR. 1–8.

13.

Raj, Desh, Junteng Jia, Jay Mahadeokar, et al.. (2023). Anchored Speech Recognition with Neural Transducers. 1–5. 1 indexed citations

14.

Jia, Junteng, et al.. (2022). Federated Domain Adaptation for ASR with Full Self-Supervision. Interspeech 2022. 536–540. 10 indexed citations

15.

Mahadeokar, Jay, Yangyang Shi, Manh Duc Le, et al.. (2022). Streaming parallel transducer beam search with fast slow cascaded encoders. Interspeech 2022. 6 indexed citations

16.

Le, Duc, Mahaveer Jain, Gil Keren, et al.. (2021). Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion. 1772–1776. 44 indexed citations

17.

Mahadeokar, Jay, Yangyang Shi, Yuan Shangguan, et al.. (2021). Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios. 2107–2111. 3 indexed citations

18.

Wang, Yongqiang, Abdelrahman Mohamed, Chunxi Liu, et al.. (2020). Transformer-Based Acoustic Modeling for Hybrid Speech Recognition. arXiv (Cornell University). 6874–6878. 147 indexed citations

19.

Mahadeokar, Jay, et al.. (2013). Faster replacement paths algorithms in case of edge or node failure for undirected, positive integer weighted graphs. Journal of Discrete Algorithms. 23. 54–62. 1 indexed citations

20.

Mahadeokar, Jay, et al.. (2012). Faster algorithm to find anti-risk path between two nodes of an undirected graph. Journal of Combinatorial Optimization. 27(4). 798–807. 1 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