David Rybach

2.8k total citations · 1 hit paper
47 papers, 1.4k citations indexed

About

David Rybach is a scholar working on Artificial Intelligence, Signal Processing and Computer Vision and Pattern Recognition. According to data from OpenAlex, David Rybach has authored 47 papers receiving a total of 1.4k indexed citations (citations by other indexed papers that have themselves been cited), including 43 papers in Artificial Intelligence, 17 papers in Signal Processing and 8 papers in Computer Vision and Pattern Recognition. Recurrent topics in David Rybach's work include Speech Recognition and Synthesis (36 papers), Natural Language Processing Techniques (19 papers) and Speech and Audio Processing (15 papers). David Rybach is often cited by papers focused on Speech Recognition and Synthesis (36 papers), Natural Language Processing Techniques (19 papers) and Speech and Audio Processing (15 papers). David Rybach collaborates with scholars based in Germany and United States. David Rybach's co-authors include Hermann Ney, Ralf Schlüter, Tara N. Sainath, Philippe Dreuw, Christian Gollan, Thomas Deselaers, Ruoming Pang, Rohit Prabhavalkar, Deepti Bhatia and Ding Zhao and has published in prestigious journals such as IEEE Transactions on Audio Speech and Language Processing, Computer Speech & Language and Technology and Disability.

In The Last Decade

David Rybach

46 papers receiving 1.2k citations

Hit 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
David Rybach Germany	18	1.1k	609	244	206	127	47	1.4k
Ricardo de Córdoba Spain	15	493 0.5×	233 0.4×	108 0.4×	202 1.0×	143 1.1×	88	709
Javier Ferreiros Spain	15	461 0.4×	164 0.3×	129 0.5×	201 1.0×	142 1.1×	88	722
Michiel Bacchiani United States	24	1.6k 1.5×	1.1k 1.8×	142 0.6×	49 0.2×	18 0.1×	66	1.9k
Satoru Hayamizu Japan	19	515 0.5×	472 0.8×	323 1.3×	49 0.2×	17 0.1×	108	1.2k
Shingo Kuroiwa Japan	13	431 0.4×	289 0.5×	102 0.4×	51 0.2×	25 0.2×	140	765
Timothy J. Hazen United States	26	2.0k 1.9×	1.3k 2.1×	312 1.3×	48 0.2×	21 0.2×	72	2.4k
Guillaume Gravier France	19	1.3k 1.2×	1.3k 2.1×	515 2.1×	50 0.2×	21 0.2×	75	1.9k
Horacio Franco United States	24	1.7k 1.6×	1.2k 1.9×	137 0.6×	40 0.2×	45 0.4×	92	2.0k
A. Garg United States	11	359 0.3×	534 0.9×	504 2.1×	68 0.3×	18 0.1×	16	1.0k
Xavier Anguera Spain	21	1.4k 1.3×	1.4k 2.3×	273 1.1×	28 0.1×	27 0.2×	82	1.8k

Countries citing papers authored by David Rybach

Since Specialization

Citations

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

Fields of papers citing papers by David Rybach

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of David Rybach

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

Variani, Ehsan, et al.. (2023). Alignment Entropy Regularization. 1–5. 1 indexed citations

2.

Chang, Shuo-Yiin, David Rybach, Tara N. Sainath, et al.. (2022). E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR. Interspeech 2022. 4995–4999. 15 indexed citations

3.

Sainath, Tara N., et al.. (2020). Emitting Word Timings with End-to-End Models. 3615–3619. 15 indexed citations

4.

Chang, Shuo-Yiin, Bo Li, David Rybach, et al.. (2020). Low Latency Speech Recognition Using End-to-End Prefetching. 1962–1966. 9 indexed citations

5.

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

6.

Zhao, Ding, Tara N. Sainath, David Rybach, et al.. (2019). Shallow-Fusion End-to-End Contextual Biasing. 1418–1422. 80 indexed citations

7.

McGraw, Ian, Rohit Prabhavalkar, Raziel Álvarez, et al.. (2016). Personalized speech recognition on mobile devices. 5955–5959. 97 indexed citations

8.

Bacchiani, Michiel & David Rybach. (2014). Context dependent state tying for speech recognition using deep neural network acoustic models. 230–234. 14 indexed citations

9.

Rybach, David, Hermann Ney, & Ralf Schlüter. (2013). Lexical Prefix Tree and WFST: A Comparison of Two Dynamic Search Concepts for LVCSR. IEEE Transactions on Audio Speech and Language Processing. 21(6). 1295–1307. 7 indexed citations

10.

Rybach, David, et al.. (2012). Hierarchical hybrid language models for open vocabulary continuous speech recognition using WFST.. Conference of the International Speech Communication Association. 46–51. 12 indexed citations

11.

Rybach, David, et al.. (2012). Joining advantages of word-conditioned and token-passing decoding. 4425–4428. 7 indexed citations

12.

Schlüter, Ralf, et al.. (2010). Parallel lexical-tree based LVCSR on multi-core processors. 1485–1488. 3 indexed citations

13.

Rybach, David & Michael Riley. (2010). Direct construction of compact context-dependency transducers from data. 218–221. 3 indexed citations

14.

Heigold, Georg, David Rybach, Ralf Schlüter, & Hermann Ney. (2009). Investigations on convex optimization using log-linear HMMs for digit string recognition. 216–219. 14 indexed citations

15.

Rybach, David, Christian Gollan, Georg Heigold, et al.. (2009). The RWTH aachen university open source speech recognition system. 2111–2114. 51 indexed citations

16.

Dreuw, Philippe, David Rybach, Christian Gollan, & Hermann Ney. (2009). Writer Adaptive Training and Writing Variant Model Refinement for Offline Arabic Handwriting Recognition. 21–25. 24 indexed citations

17.

Gollan, Christian, et al.. (2009). Investigating the use of morphological decomposition and diacritization for improving Arabic LVCSR. RWTH Publications (RWTH Aachen). 2679–2682. 31 indexed citations

18.

Dreuw, Philippe, David Rybach, Thomas Deselaers, Morteza Zahedi, & Hermann Ney. (2007). Speech recognition techniques for a sign language recognition system. 2513–2516. 94 indexed citations

19.

Dreuw, Philippe, Thomas Deselaers, David Rybach, Daniel Keysers, & Hermann Ney. (2006). Tracking Using Dynamic Programming for Appearance-Based Sign Language Recognition. 293–298. 43 indexed citations

20.

Zahedi, Morteza, Philippe Dreuw, David Rybach, Thomas Deselaers, & Hermann Ney. (2006). Geometric Features for Improving Continuous Appearance-based Sign Language Recognition. 104.1–104.10. 14 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