Cyril Allauzen

Cyril Allauzen

Cyril Allauzen is a research scientist at Google in New York. His main research interests are in finite-state methods and their applications to text, speech and natural language processing and machine learning. Before joining Google, he worked as a researcher at AT&T Labs Research and at NYU's Courant Institute of Mathematical Sciences. Cyril received his Ph.D. in computer science from the Université de Marne-la-Vallée in 2001.

Cyril is an author of the OpenFst Library, the OpenKernel Library and the GRM Library.

Research Areas

Authored Publications
33 results

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Global Normalization for Streaming Speech Recognition in a Modular Framework
    Cyril Allauzen
    David Rybach
    Ehsan Variani
    Ke Wu
    Matt Shannon
    Michael Riley
    arxiv (2022)
    On Weight Interpolation of the Hybrid Autoregressive Transducer Model
    Bhuvana Ramabhadran
    Cyril Allauzen
    David Rybach
    Ehsan Variani
    Michael D. Riley
    Tongzhou Chen
    Interspeech 2022, Interspeech 2022 (2022) (to appear)
    E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
    W. Ronny Huang
    Shuo-yiin Chang
    David Rybach
    Tara N Sainath
    Rohit Prabhavalkar
    Cyril Allauzen
    Cal Peyser
    Zhiyun Lu
    Interspeech 2022 (2022) (to appear)
    An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling
    Tara N Sainath
    Yanzhang (Ryan) He
    Arun Narayanan
    Rami Botros
    Ruoming Pang
    David Johannes Rybach
    Cyril Allauzen
    Ehsan Variani
    James Qin
    Quoc-Nam Le-The
    Alex Gruenstein
    Anmol Gulati
    Bo Li
    Cal Peyser
    Chung-Cheng Chiu
    Diamantino A. Caseiro
    Emmanuel Guzman
    Ian Carmichael McGraw
    Jiahui Yu
    Michael D. Riley
    Pat Rondon
    Qiao Liang
    Sepand Mavandadi
    Shuo-yiin Chang
    Trevor Deatrick Strohman
    W. Ronny Huang
    Wei Li
    Yonghui Wu
    Yu Zhang
    Interspeech (2021) (to appear)
    Hybrid Autoregressive Transducer (HAT)
    Ehsan Variani
    David Rybach
    Cyril Allauzen
    Michael Riley
    ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, Spain, pp. 6139-6143
    Contextual Recovery of Out-of-Lattice Named Entities in Automatic Speech Recognition
    Jack Serrino
    Leonid Velikovich
    Petar Aleksic
    Cyril Allauzen
    ISCA Interspeech 2019, ISCA, Graz, Austria (2019), pp. 3830-3834
    Federated Learning of N-gram Language Models
    Adeline Wong
    Ananda Theertha Suresh
    Cyril Allauzen
    Francoise Beaufays
    Michael Riley
    Mingqing Chen
    Rajiv Mathews
    The SIGNLL Conference on Computational Natural Language Learning (2019)
    Algorithms for Weighted Finite Automata with Failure Transitions
    Cyril Allauzen
    Michael Riley
    International Conference of Implementation and Applications of Automata (CIAA) (2018), pp. 46-58
    Transliterated mobile keyboard input via weighted finite-state transducers
    Lars Hellsten
    Brian Roark
    Prasoon Goyal
    Cyril Allauzen
    Francoise Beaufays
    Tom Ouyang
    Michael Riley
    David Rybach
    Proceedings of the 13th International Conference on Finite State Methods and Natural Language Processing (FSMNLP) (2017)
    Distributed representation and estimation of WFST-based n-gram models
    Cyril Allauzen
    Michael Riley
    Brian Roark
    Proceedings of the ACL Workshop on Statistical NLP and Weighted Automata (StatFSM) (2016), pp. 32-41
    Search on Google Scholar