Rohit Prabhavalkar

4.0k total citations · 1 hit paper
59 papers, 1.8k citations indexed

About

Rohit Prabhavalkar is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, Rohit Prabhavalkar has authored 59 papers receiving a total of 1.8k indexed citations (citations by other indexed papers that have themselves been cited), including 57 papers in Artificial Intelligence, 39 papers in Signal Processing and 3 papers in Computer Vision and Pattern Recognition. Recurrent topics in Rohit Prabhavalkar's work include Speech Recognition and Synthesis (52 papers), Speech and Audio Processing (33 papers) and Music and Audio Processing (26 papers). Rohit Prabhavalkar is often cited by papers focused on Speech Recognition and Synthesis (52 papers), Speech and Audio Processing (33 papers) and Music and Audio Processing (26 papers). Rohit Prabhavalkar collaborates with scholars based in United States, United Kingdom and Taiwan. Rohit Prabhavalkar's co-authors include Tara N. Sainath, Kanishka Rao, Haşim Sak, Raziel Álvarez, Bo Li, Anjuli Kannan, Golan Pundak, Yanzhang He, Ruoming Pang and Ding Zhao and has published in prestigious journals such as Proceedings of the IEEE, IEEE/ACM Transactions on Audio Speech and Language Processing and arXiv (Cornell University).

In The Last Decade

Rohit Prabhavalkar

56 papers receiving 1.5k citations

Hit Papers

1 papers align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

Streaming End-to-end Speech Recognition for Mobile Devices

2019 345 citations Yanzhang He, Tara N. Sainath et al. profile →

Peers — A (Enhanced Table)

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

Name	h						Papers	Cites
Rohit Prabhavalkar United States	21	1.6k	1.0k	154	47	38	59	1.8k
Khe Chai Sim Singapore	21	1.6k 1.0×	1.2k 1.1×	157 1.0×	33 0.7×	30 0.8×	111	1.8k
Shigeki Karita Japan	13	1.5k 1.0×	1.1k 1.0×	116 0.8×	36 0.8×	36 0.9×	26	1.8k
Kanishka Rao India	17	1.6k 1.0×	967 0.9×	278 1.8×	50 1.1×	122 3.2×	53	1.9k
K.-F. Lee United States	9	1.1k 0.7×	895 0.9×	201 1.3×	25 0.5×	27 0.7×	11	1.2k
Jahn Heymann Germany	17	1.4k 0.9×	1.5k 1.4×	101 0.7×	50 1.1×	21 0.6×	27	1.8k
David Rybach Germany	18	1.1k 0.7×	609 0.6×	244 1.6×	39 0.8×	50 1.3×	47	1.4k
Seiichi Nakagawa Japan	21	1.3k 0.8×	1.0k 1.0×	187 1.2×	41 0.9×	32 0.8×	257	1.6k
P. Nguyen United States	11	826 0.5×	665 0.6×	177 1.1×	34 0.7×	26 0.7×	18	1.1k
Michiel Bacchiani United States	24	1.6k 1.0×	1.1k 1.0×	142 0.9×	49 1.0×	22 0.6×	66	1.9k

Countries citing papers authored by Rohit Prabhavalkar

Since Specialization

Citations

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

Fields of papers citing papers by Rohit Prabhavalkar

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Rohit Prabhavalkar

This figure shows the co-authorship network connecting the top 25 collaborators of Rohit Prabhavalkar. A scholar is included among the top collaborators of Rohit Prabhavalkar 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 Rohit Prabhavalkar. Rohit Prabhavalkar 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

1.

Wang, Weiran, Rohit Prabhavalkar, Zhong Meng, et al.. (2024). Massive End-to-end Speech Recognition Models with Time Reduction. 6206–6217. 1 indexed citations

2.

Ding, Shaojin, Yanzhang He, Bo Li, et al.. (2024). USM-Lite: Quantization and Sparsity Aware Fine-Tuning for Speech Recognition with Universal Speech Models. 10756–10760. 1 indexed citations

3.

Wu, Zelin, Gan Song, Christopher Li, et al.. (2024). Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR. 315–323.

4.

Picheny, Michael, et al.. (2023). A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale. 1–5.

5.

Meng, Zhong, Rohit Prabhavalkar, Andrew Rosenberg, et al.. (2023). Improving Joint Speech-Text Representations Without Alignment. 1354–1358. 1 indexed citations

6.

Yang, Chao-Han Huck, Bo Li, Yu Zhang, et al.. (2023). How to Estimate Model Transferability of Pre-Trained Speech Models?. 4 indexed citations

7.

Hernandez, Steven M., Ding Zhao, Shaojin Ding, et al.. (2023). Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models. 1–5. 4 indexed citations

8.

Yang, Chao-Han Huck, Bo Li, Yu Zhang, et al.. (2023). From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition. 1–5. 14 indexed citations

9.

Tripathi, Anshuman, Jaeyoung Kim, Lu Han, et al.. (2023). Cross-Training: A Semi-Supervised Training Scheme for Speech Recognition. 1–5. 2 indexed citations

10.

Bruguier, Antoine, Duc Le, Rohit Prabhavalkar, et al.. (2022). Neural-FST Class Language Model for End-to-End Speech Recognition. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 18. 6107–6111. 3 indexed citations

11.

Irie, Kazuki, Rohit Prabhavalkar, Anjuli Kannan, et al.. (2019). Model Unit Exploration for Sequence-to-Sequence Speech Recognition.. arXiv (Cornell University). 5 indexed citations

12.

Chang, Shuo-Yiin, Rohit Prabhavalkar, Yanzhang He, Tara N. Sainath, & Gabor Simko. (2019). Joint Endpointing and Decoding with End-to-end Models. 5626–5630. 22 indexed citations

13.

Pundak, Golan, Tara N. Sainath, Rohit Prabhavalkar, Anjuli Kannan, & Ding Zhao. (2018). Deep Context: End-to-end Contextual Speech Recognition. 418–425. 95 indexed citations

14.

Sainath, Tara N., Chung‐Cheng Chiu, Rohit Prabhavalkar, et al.. (2018). Improving the Performance of Online Neural Transducer Models. 5864–5868. 28 indexed citations

15.

Prabhavalkar, Rohit, Kanishka Rao, Tara N. Sainath, et al.. (2017). A Comparison of Sequence-to-Sequence Models for Speech Recognition. 939–943. 178 indexed citations

16.

Rao, Kanishka, Haşim Sak, & Rohit Prabhavalkar. (2017). Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer. 193–199. 193 indexed citations

17.

Prabhavalkar, Rohit, et al.. (2017). An Analysis of “Attention” in Sequence-to-Sequence Models. 3702–3706. 21 indexed citations

18.

Álvarez, Raziel, Rohit Prabhavalkar, & Anton Bakhtin. (2016). On the Efficient Representation and Execution of Deep Acoustic Models. 2746–2750. 26 indexed citations

19.

Prabhavalkar, Rohit. (2013). Discriminative Articulatory Feature-based Pronunciation Models with Application to Spoken Term Detection. OhioLink ETD Center (Ohio Library and Information Network). 3 indexed citations

20.

Prabhavalkar, Rohit, et al.. (2010). Investigations into the Crandem Approach to Word Recognition. North American Chapter of the Association for Computational Linguistics. 725–728. 2 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