@inproceedings{bedyakin-mikhaylovskiy-2021-language,
    title = "Language {ID} Prediction from Speech Using Self-Attentive Pooling",
    author = "Bedyakin, Roman  and
      Mikhaylovskiy, Nikolay",
    editor = {Vylomova, Ekaterina  and
      Salesky, Elizabeth  and
      Mielke, Sabrina  and
      Lapesa, Gabriella  and
      Kumar, Ritesh  and
      Hammarstr{\"o}m, Harald  and
      Vuli{\'c}, Ivan  and
      Korhonen, Anna  and
      Reichart, Roi  and
      Ponti, Edoardo Maria  and
      Cotterell, Ryan},
    booktitle = "Proceedings of the Third Workshop on Computational Typology and Multilingual NLP",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2021.sigtyp-1.12/",
    doi = "10.18653/v1/2021.sigtyp-1.12",
    pages = "130--135",
    abstract = "This memo describes NTR-TSU submission for SIGTYP 2021 Shared Task on predicting language IDs from speech. Spoken Language Identification (LID) is an important step in a multilingual Automated Speech Recognition (ASR) system pipeline. For many low-resource and endangered languages, only single-speaker recordings may be available, demanding a need for domain and speaker-invariant language ID systems. In this memo, we show that a convolutional neural network with a Self-Attentive Pooling layer shows promising results for the language identification task."
}