![](https://dblp.org/img/logo.ua.320x120.png)
![](https://dblp.org/img/dropdown.dark.16x16.png)
![](https://dblp.org/img/peace.dark.16x16.png)
Остановите войну!
for scientists:
![search dblp search dblp](https://dblp.org/img/search.dark.16x16.png)
![search dblp](https://dblp.org/img/search.dark.16x16.png)
default search action
Cyril Allauzen
Person information
Refine list
![note](https://dblp.org/img/note-mark.dark.12x12.png)
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c57]Kyle Gorman, Cyril Allauzen:
A* shortest string decoding for non-idempotent semirings. EACL (1) 2024: 732-739 - [c56]W. Ronny Huang, Cyril Allauzen, Tongzhou Chen, Kilol Gupta, Ke Hu, James Qin, Yu Zhang, Yongqiang Wang, Shuo-Yiin Chang, Tara N. Sainath:
Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study. ICASSP 2024: 13306-13310 - [i12]W. Ronny Huang, Cyril Allauzen, Tongzhou Chen, Kilol Gupta, Ke Hu, James Qin, Yu Zhang, Yongqiang Wang, Shuo-Yiin Chang, Tara N. Sainath:
Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study. CoRR abs/2401.12789 (2024) - 2023
- [c55]Tongzhou Chen, Cyril Allauzen, Yinghui Huang, Daniel S. Park, David Rybach, W. Ronny Huang, Rodrigo Cabrera, Kartik Audhkhasi, Bhuvana Ramabhadran, Pedro J. Moreno, Michael Riley:
Large-Scale Language Model Rescoring on Long-Form Data. ICASSP 2023: 1-5 - [c54]W. Ronny Huang, Shuo-Yiin Chang, Tara N. Sainath, Yanzhang He, David Rybach, Robert David, Rohit Prabhavalkar, Cyril Allauzen, Cal Peyser, Trevor D. Strohman:
E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model. ICASSP 2023: 1-5 - [c53]Tara N. Sainath, Rohit Prabhavalkar, Diamantino Caseiro, Pat Rondon, Cyril Allauzen:
Improving Contextual Biasing with Text Injection. ICASSP 2023: 1-5 - [c52]Ehsan Variani, Ke Wu, David Rybach, Cyril Allauzen, Michael Riley:
Alignment Entropy Regularization. ICASSP 2023: 1-5 - [c51]Cyril Allauzen:
Weighted Finite Automata with Failure Transitions: Algorithms and Applications. ICGI 2023: 6 - [i11]Tongzhou Chen, Cyril Allauzen, Yinghui Huang, Daniel S. Park, David Rybach, W. Ronny Huang, Rodrigo Cabrera, Kartik Audhkhasi, Bhuvana Ramabhadran, Pedro J. Moreno, Michael Riley:
Large-scale Language Model Rescoring on Long-form Data. CoRR abs/2306.08133 (2023) - 2022
- [c50]Ehsan Variani, Michael Riley, David Rybach, Cyril Allauzen, Tongzhou Chen, Bhuvana Ramabhadran:
On Adaptive Weight Interpolation of the Hybrid Autoregressive Transducer. INTERSPEECH 2022: 1646-1650 - [c49]W. Ronny Huang, Shuo-Yiin Chang, David Rybach, Tara N. Sainath, Rohit Prabhavalkar, Cal Peyser, Zhiyun Lu, Cyril Allauzen:
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR. INTERSPEECH 2022: 4995-4999 - [c48]Ehsan Variani, Ke Wu, Michael D. Riley, David Rybach, Matt Shannon, Cyril Allauzen:
Global Normalization for Streaming Speech Recognition in a Modular Framework. NeurIPS 2022 - [i10]Kyle Gorman, Cyril Allauzen:
A* shortest string decoding for non-idempotent semirings. CoRR abs/2204.07236 (2022) - [i9]W. Ronny Huang, Shuo-Yiin Chang, David Rybach, Rohit Prabhavalkar, Tara N. Sainath, Cyril Allauzen, Cal Peyser, Zhiyun Lu:
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR. CoRR abs/2204.10749 (2022) - [i8]Ehsan Variani, Ke Wu, Michael Riley, David Rybach, Matt Shannon, Cyril Allauzen:
Global Normalization for Streaming Speech Recognition in a Modular Framework. CoRR abs/2205.13674 (2022) - [i7]W. Ronny Huang, Shuo-Yiin Chang, Tara N. Sainath, Yanzhang He, David Rybach, Robert David, Rohit Prabhavalkar, Cyril Allauzen, Cal Peyser, Trevor D. Strohman:
E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model. CoRR abs/2211.15432 (2022) - [i6]Ehsan Variani, Ke Wu, David Rybach, Cyril Allauzen, Michael Riley:
Alignment Entropy Regularization. CoRR abs/2212.12442 (2022) - 2021
- [c47]Tara N. Sainath, Yanzhang He, Arun Narayanan, Rami Botros, Ruoming Pang, David Rybach, Cyril Allauzen, Ehsan Variani, James Qin, Quoc-Nam Le-The, Shuo-Yiin Chang, Bo Li, Anmol Gulati, Jiahui Yu, Chung-Cheng Chiu, Diamantino Caseiro, Wei Li, Qiao Liang, Pat Rondon:
An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling. Interspeech 2021: 1777-1781 - [c46]Cyril Allauzen, Ehsan Variani, Michael Riley, David Rybach, Hao Zhang:
A Hybrid Seq-2-Seq ASR Design for On-Device and Server Applications. Interspeech 2021: 4044-4048 - 2020
- [c45]Ehsan Variani, David Rybach, Cyril Allauzen, Michael Riley:
Hybrid Autoregressive Transducer (HAT). ICASSP 2020: 6139-6143 - [i5]Ehsan Variani, David Rybach, Cyril Allauzen, Michael Riley:
Hybrid Autoregressive Transducer (hat). CoRR abs/2003.07705 (2020)
2010 – 2019
- 2019
- [c44]Mingqing Chen, Ananda Theertha Suresh, Rajiv Mathews, Adeline Wong, Cyril Allauzen, Françoise Beaufays, Michael Riley:
Federated Learning of N-Gram Language Models. CoNLL 2019: 121-130 - [c43]Marco Cognetta, Cyril Allauzen, Michael Riley:
On the Compression of Lexicon Transducers. FSMNLP 2019: 18-26 - [c42]Jack Serrino, Leonid Velikovich, Petar S. Aleksic, Cyril Allauzen:
Contextual Recovery of Out-of-Lattice Named Entities in Automatic Speech Recognition. INTERSPEECH 2019: 3830-3834 - [i4]Mingqing Chen, Ananda Theertha Suresh, Rajiv Mathews, Adeline Wong, Cyril Allauzen, Françoise Beaufays, Michael Riley:
Federated Learning of N-gram Language Models. CoRR abs/1910.03432 (2019) - 2018
- [c41]Cyril Allauzen, Michael D. Riley:
Algorithms for Weighted Finite Automata with Failure Transitions. CIAA 2018: 46-58 - 2017
- [c40]Lars Hellsten, Brian Roark, Prasoon Goyal, Cyril Allauzen, Françoise Beaufays, Tom Ouyang, Michael Riley, David Rybach:
Transliterated Mobile Keyboard Input via Weighted Finite-State Transducers. FSMNLP 2017: 10-19 - 2015
- [c39]Petar S. Aleksic, Cyril Allauzen, David Elson, Aleksandar Kracun, Diego Melendo Casado, Pedro J. Moreno:
Improved recognition of contact names in voice commands. ICASSP 2015: 5172-5175 - [c38]Petar S. Aleksic, Mohammadreza Ghodsi, Assaf Hurwitz Michaely, Cyril Allauzen, Keith B. Hall, Brian Roark, David Rybach, Pedro J. Moreno:
Bringing contextual information to google speech recognition. INTERSPEECH 2015: 468-472 - [c37]Keith B. Hall, Eunjoon Cho, Cyril Allauzen, Françoise Beaufays, Noah Coccaro, Kaisuke Nakajima, Michael Riley, Brian Roark, David Rybach, Linda Zhang:
Composition-based on-the-fly rescoring for salient n-gram biasing. INTERSPEECH 2015: 1418-1422 - [c36]Cyril Allauzen, Michael Riley:
Rapid vocabulary addition to context-dependent decoder graphs. INTERSPEECH 2015: 2112-2116 - 2014
- [j10]Cyril Allauzen, Bill Byrne, Adrià de Gispert, Gonzalo Iglesias, Michael Riley:
Pushdown Automata in Statistical Machine Translation. Comput. Linguistics 40(3): 687-723 (2014) - [c35]Ke Wu, Cyril Allauzen, Keith B. Hall, Michael Riley, Brian Roark:
Encoding linear models as weighted finite-state transducers. INTERSPEECH 2014: 1258-1262 - 2013
- [c34]Brian Roark, Cyril Allauzen, Michael Riley:
Smoothed marginal distribution constraints for language modeling. ACL (1) 2013: 43-52 - [c33]Hasim Sak, Cyril Allauzen, Kaisuke Nakajima, Françoise Beaufays:
Mixture of mixture n-gram language models. ASRU 2013: 31-36 - [c32]Hasim Sak, Françoise Beaufays, Kaisuke Nakajima, Cyril Allauzen:
Language model verbalization for automatic speech recognition. ICASSP 2013: 8262-8266 - [c31]Cyril Allauzen, Michael Riley:
Pre-initialized composition for large-vocabulary speech recognition. INTERSPEECH 2013: 666-670 - [c30]Hasim Sak, Yun-Hsuan Sung, Françoise Beaufays, Cyril Allauzen:
Written-domain language modeling for automatic speech recognition. INTERSPEECH 2013: 675-679 - 2012
- [c29]Brian Roark, Richard Sproat, Cyril Allauzen, Michael Riley, Jeffrey Sorensen, Terry Tai:
The OpenGrm open-source finite-state grammar software libraries. ACL (System Demonstrations) 2012: 61-66 - [c28]Cyril Allauzen, Edward Benson, Ciprian Chelba, Michael Riley, Johan Schalkwyk:
Voice Query Refinement. INTERSPEECH 2012: 2462-2465 - [c27]Cyril Allauzen, Michael Riley:
A Pushdown Transducer Extension for the OpenFst Library. CIAA 2012: 66-77 - 2011
- [j9]Cyril Allauzen, Mehryar Mohri, Ashish Rastogi:
General Algorithms for Testing the Ambiguity of Finite Automata and the Double-Tape Ambiguity of Finite-State Transducers. Int. J. Found. Comput. Sci. 22(4): 883-904 (2011) - [j8]Cyril Allauzen, Corinna Cortes, Mehryar Mohri:
A Dual Coordinate Descent Algorithm for SVMs Combined with Rational Kernels. Int. J. Found. Comput. Sci. 22(8): 1761-1779 (2011) - [j7]Cyril Allauzen, Michael Riley, Johan Schalkwyk:
A Filter-Based Algorithm for Efficient Composition of Finite-State Transducers. Int. J. Found. Comput. Sci. 22(8): 1781-1795 (2011) - [c26]Gonzalo Iglesias, Cyril Allauzen, William Byrne, Adrià de Gispert, Michael Riley:
Hierarchical Phrase-based Translation Representations. EMNLP 2011: 1373-1383 - [c25]Jeffrey Sorensen, Cyril Allauzen:
Unary Data Structures for Language Models. INTERSPEECH 2011: 1425-1428 - [c24]Cyril Allauzen, Michael Riley:
Bayesian Language Model Interpolation for Mobile Speech Input. INTERSPEECH 2011: 1429-1432 - 2010
- [c23]Brandon Ballinger, Cyril Allauzen, Alexander Gruenstein, Johan Schalkwyk:
On-demand language model interpolation for mobile speech input. INTERSPEECH 2010: 1812-1815 - [c22]Cyril Allauzen, Shankar Kumar, Wolfgang Macherey, Mehryar Mohri, Michael Riley:
Expected Sequence Similarity Maximization. HLT-NAACL 2010: 957-965 - [c21]Cyril Allauzen, Corinna Cortes, Mehryar Mohri:
Large-Scale Training of SVMs with Automata Kernels. CIAA 2010: 17-27 - [c20]Cyril Allauzen, Michael Riley, Johan Schalkwyk:
Filters for Efficient Composition of Weighted Finite-State Transducers. CIAA 2010: 28-38
2000 – 2009
- 2009
- [j6]Cyril Allauzen, Mehryar Mohri:
N-Way Composition of Weighted Finite-State Transducers. Int. J. Found. Comput. Sci. 20(4): 613-627 (2009) - [c19]Cyril Allauzen, Michael Riley, Johan Schalkwyk:
A generalized composition algorithm for weighted finite-state transducers. INTERSPEECH 2009: 1203-1206 - [c18]Michael Riley, Cyril Allauzen, Martin Jansche:
OpenFst: An Open-Source, Weighted Finite-State Transducer Library and its Applications to Speech and Language. HLT-NAACL (Tutorial Abstracts) 2009: 9-10 - [i3]Cyril Allauzen, Mehryar Mohri:
Linear-Space Computation of the Edit-Distance between a String and a Finite Automaton. CoRR abs/0904.4686 (2009) - 2008
- [c17]Cyril Allauzen, Mehryar Mohri, Ashish Rastogi:
General Algorithms for Testing the Ambiguity of Finite Automata. Developments in Language Theory 2008: 108-120 - [c16]Cyril Allauzen, Mehryar Mohri, Ameet Talwalkar:
Sequence kernels for predicting protein essentiality. ICML 2008: 9-16 - [c15]Cyril Allauzen, Mehryar Mohri:
3-Way Composition of Weighted Finite-State Transducers. CIAA 2008: 262-273 - [i2]Cyril Allauzen, Mehryar Mohri:
3-Way Composition of Weighted Finite-State Transducers. CoRR abs/0802.1465 (2008) - [i1]Cyril Allauzen, Mehryar Mohri, Ashish Rastogi:
General Algorithms for Testing the Ambiguity of Finite Automata. CoRR abs/0802.3254 (2008) - 2007
- [c14]Cyril Allauzen, Michael Riley, Johan Schalkwyk, Wojciech Skut, Mehryar Mohri:
OpenFst: A General and Efficient Weighted Finite-State Transducer Library. CIAA 2007: 11-23 - 2006
- [c13]Cyril Allauzen, Mehryar Mohri:
A Unified Construction of the Glushkov, Follow, and Antimirov Automata. MFCS 2006: 110-121 - 2005
- [j5]Cyril Allauzen, Mehryar Mohri, Brian Roark:
The design principles and algorithms of a weighted grammar library. Int. J. Found. Comput. Sci. 16(3): 403-421 (2005) - [c12]Vincent Goffin, Cyril Allauzen, Enrico Bocchieri, Dilek Hakkani-Tür, Andrej Ljolje, Sarangarajan Parthasarathy, Mazin G. Rahim, Giuseppe Riccardi, Murat Saraçlar:
The AT&T WATSON Speech Recognizer. ICASSP (1) 2005: 1033-1036 - [c11]S. Parthasarathy, Cyril Allauzen, R. Munkong:
Robust access to large structured data using voice form-filling. INTERSPEECH 2005: 2493-2496 - 2004
- [j4]Cyril Allauzen, Mehryar Mohri:
An optimal pre-determinization algorithm for weighted transducers. Theor. Comput. Sci. 328(1-2): 3-18 (2004) - [c10]Mehryar Mohri, Cyril Allauzen, Michael Riley:
Statistical Modeling for Unit Selection in Speech Synthesis. ACL 2004: 55-62 - [c9]Cyril Allauzen, Mehryar Mohri, Michael Riley, Brian Roark:
A generalized construction of integrated speech recognition transducers. ICASSP (1) 2004: 761-764 - [c8]Cyril Allauzen, Mehryar Mohri, Brian Roark:
A General Weighted Grammar Library. CIAA 2004: 23-34 - 2003
- [j3]Cyril Allauzen, Mehryar Mohri:
Finitely Subsequential Transducers. Int. J. Found. Comput. Sci. 14(6): 983-994 (2003) - [j2]Cyril Allauzen, Mehryar Mohri:
Efficient Algorithms for Testing the Twins Property. J. Autom. Lang. Comb. 8(2): 117-144 (2003) - [c7]Cyril Allauzen, Mehryar Mohri, Brian Roark:
Generalized Algorithms for Constructing Statistical Language Models. ACL 2003: 40-47 - [c6]Cyril Allauzen, Mehryar Mohri:
Generalized optimization algorithm for speech recognition transducers. ICASSP (1) 2003: 352-355 - [c5]Cyril Allauzen, Mehryar Mohri:
An Efficient Pre-determinization Algorithm. CIAA 2003: 83-95 - 2002
- [c4]Cyril Allauzen, Mehryar Mohri:
p-Subsequentiable Transducers. CIAA 2002: 24-34 - 2001
- [c3]Cyril Allauzen, Maxime Crochemore, Mathieu Raffinot:
Efficient Experimental String Matching by Weak Factor Recognition. CPM 2001: 51-72 - 2000
- [j1]Cyril Allauzen, Mathieu Raffinot:
Simple Optimal String Matching Algorithm. J. Algorithms 36(1): 102-116 (2000) - [c2]Cyril Allauzen, Mathieu Raffinot:
Simple Optimal String Matching Algorithm. CPM 2000: 364-374
1990 – 1999
- 1999
- [c1]Cyril Allauzen, Maxime Crochemore, Mathieu Raffinot:
Factor Oracle: A New Structure for Pattern Matching. SOFSEM 1999: 295-310
Coauthor Index
![](https://dblp.org/img/cog.dark.24x24.png)
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-08-08 19:13 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint