Cyril Allauzen

2.4k total citations
55 papers, 926 citations indexed

About

Cyril Allauzen is a scholar working on Artificial Intelligence, Computational Theory and Mathematics and Signal Processing. According to data from OpenAlex, Cyril Allauzen has authored 55 papers receiving a total of 926 indexed citations (citations by other indexed papers that have themselves been cited), including 52 papers in Artificial Intelligence, 14 papers in Computational Theory and Mathematics and 9 papers in Signal Processing. Recurrent topics in Cyril Allauzen's work include Natural Language Processing Techniques (30 papers), Speech Recognition and Synthesis (29 papers) and Algorithms and Data Compression (19 papers). Cyril Allauzen is often cited by papers focused on Natural Language Processing Techniques (30 papers), Speech Recognition and Synthesis (29 papers) and Algorithms and Data Compression (19 papers). Cyril Allauzen collaborates with scholars based in United States, France and United Kingdom. Cyril Allauzen's co-authors include Mehryar Mohri, Michael Riley, Brian Roark, Murat Saraçlar, Johan Schalkwyk, Jeffrey Sorensen, David Rybach, Françoise Beaufays, Petar Aleksic and Keith Hall and has published in prestigious journals such as Theoretical Computer Science, Computational Linguistics and Journal of Algorithms.

In The Last Decade

Cyril Allauzen

53 papers receiving 797 citations

Peers — A (Enhanced Table)

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

Name h Career Trend Papers Cites
Cyril Allauzen United States 17 852 242 82 58 36 55 926
Gabor Simko United States 11 228 0.3× 188 0.8× 60 0.7× 24 0.4× 24 0.7× 21 418
Allen L. Gorin United States 17 1.1k 1.3× 131 0.5× 18 0.2× 72 1.2× 9 0.3× 63 1.2k
M. Padmanabhan United States 18 749 0.9× 589 2.4× 13 0.2× 155 2.7× 20 0.6× 61 947
Hozumi Tanaka Japan 15 554 0.7× 54 0.2× 41 0.5× 74 1.3× 9 0.3× 75 652
S. Ortmanns Germany 12 647 0.8× 328 1.4× 8 0.1× 157 2.7× 20 0.6× 18 739
Ebru Arısoy Türkiye 15 888 1.0× 242 1.0× 6 0.1× 211 3.6× 15 0.4× 40 1.0k
Mikio Yamamoto Japan 11 541 0.6× 284 1.2× 7 0.1× 66 1.1× 8 0.2× 45 687
Toshiyuki Takezawa Japan 15 860 1.0× 318 1.3× 12 0.1× 72 1.2× 5 0.1× 78 1.0k
Long Nguyen United States 19 968 1.1× 512 2.1× 10 0.1× 121 2.1× 7 0.2× 77 1.1k
Weidong Chen China 11 366 0.4× 79 0.3× 64 0.8× 99 1.7× 5 0.1× 41 519

Countries citing papers authored by Cyril Allauzen

Since Specialization
Citations

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

Fields of papers citing papers by Cyril Allauzen

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Cyril Allauzen

This figure shows the co-authorship network connecting the top 25 collaborators of Cyril Allauzen. A scholar is included among the top collaborators of Cyril Allauzen 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 Cyril Allauzen. Cyril Allauzen 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.
Allauzen, Cyril, Ke Hu, James Qin, et al.. (2024). Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study. 13306–13310. 2 indexed citations
2.
Variani, Ehsan, et al.. (2023). Alignment Entropy Regularization. 1–5. 1 indexed citations
3.
Chen, Mingqing, Ananda Theertha Suresh, Rajiv Mathews, et al.. (2019). Federated Learning of N-Gram Language Models. 28 indexed citations
4.
Allauzen, Cyril, et al.. (2019). On the Compression of Lexicon Transducers. 18–26.
5.
Allauzen, Cyril, Michael Riley, & Brian Roark. (2016). Distributed representation and estimation of WFST-based n-gram models. 32–41. 3 indexed citations
6.
Wu, Ke, Cyril Allauzen, Keith Hall, Michael Riley, & Brian Roark. (2014). Encoding linear models as weighted finite-state transducers. 1258–1262. 16 indexed citations
7.
Roark, Brian, Cyril Allauzen, & Michael Riley. (2013). Smoothed marginal distribution constraints for language modeling. Meeting of the Association for Computational Linguistics. 43–52. 6 indexed citations
8.
Allauzen, Cyril, Corinna Cortes, & Mehryar Mohri. (2013). SVM Optimization for Lattice Kernels.
9.
Sak, Haşim, et al.. (2013). Mixture of mixture n-gram language models. 31–36. 2 indexed citations
10.
Allauzen, Cyril & Michael Riley. (2013). Pre-initialized composition for large-vocabulary speech recognition. 666–670. 5 indexed citations
11.
Allauzen, Cyril, et al.. (2011). Hierarchical Phrase-based Translation Representations. Cambridge University Engineering Department Publications Database. 1373–1383. 11 indexed citations
12.
Chelba, Ciprian, Johan Schalkwyk, Boulos Harb, et al.. (2011). Language Modeling for Automatic Speech Recognition Meets the Web: Google Search by Voice. 2 indexed citations
13.
Allauzen, Cyril, Shankar Kumar, Wolfgang Macherey, Mehryar Mohri, & Michael Riley. (2010). Expected Sequence Similarity Maximization. North American Chapter of the Association for Computational Linguistics. 957–965. 3 indexed citations
14.
Riley, Michael, Cyril Allauzen, & Martin Jansche. (2009). OpenFst. 9–10. 18 indexed citations
15.
Allauzen, Cyril, Michael Riley, & Johan Schalkwyk. (2009). A generalized composition algorithm for weighted finite-state transducers. 1203–1206. 29 indexed citations
16.
Parthasarathy, Srinivas, et al.. (2005). Robust access to large structured data using voice form-filling. 2493–2496. 3 indexed citations
17.
Allauzen, Cyril, Mehryar Mohri, & Michael Riley. (2004). Statistical modeling for unit selection in speech synthesis. 55–es. 12 indexed citations
18.
Allauzen, Cyril & Mehryar Mohri. (2004). An optimal pre-determinization algorithm for weighted transducers. Theoretical Computer Science. 328(1-2). 3–18. 5 indexed citations
19.
Allauzen, Cyril, Mehryar Mohri, & Brian Roark. (2003). Generalized algorithms for constructing statistical language models. 1. 40–47. 94 indexed citations
20.
Allauzen, Cyril & Mehryar Mohri. (2002). p-subsequentiable transducers. 24–34. 3 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 Gabor Simko Breakdown of academic impact, for papers by Allen L. Gorin Breakdown of academic impact, for papers by M. Padmanabhan Breakdown of academic impact, for papers by Hozumi Tanaka Breakdown of academic impact, for papers by S. Ortmanns Breakdown of academic impact, for papers by Ebru Arısoy Breakdown of academic impact, for papers by Mikio Yamamoto Breakdown of academic impact, for papers by Toshiyuki Takezawa Breakdown of academic impact, for papers by Long Nguyen Breakdown of academic impact, for papers by Weidong Chen
Rankless by CCL
2026