@inproceedings{kipyatkova-karpov-2020-class,
    title = "Class-based {LSTM} {R}ussian Language Model with Linguistic Information",
    author = "Kipyatkova, Irina  and
      Karpov, Alexey",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.lrec-1.300/",
    pages = "2470--2474",
    language = "eng",
    ISBN = "979-10-95546-34-4",
    abstract = "In the paper, we present class-based LSTM Russian language models (LMs) with classes generated with the use of both word frequency and linguistic information data, obtained with the help of the ``VisualSynan'' software from the AOT project. We have created LSTM LMs with various numbers of classes and compared them with word-based LM and class-based LM with word2vec class generation in terms of perplexity, training time, and WER. In addition, we performed a linear interpolation of LSTM language models with the baseline 3-gram language model. The LSTM language models were used for very large vocabulary continuous Russian speech recognition at an N-best list rescoring stage. We achieved significant progress in training time reduction with only slight degradation in recognition accuracy comparing to the word-based LM. In addition, our LM with classes generated using linguistic information outperformed LM with classes generated using word2vec. We achieved WER of 14.94 {\%} at our own speech corpus of continuous Russian speech that is 15 {\%} relative reduction with respect to the baseline 3-gram model."
}