@inproceedings{celano-2021-resnet,
    title = "A {R}es{N}et-50-Based Convolutional Neural Network Model for Language {ID} Identification from Speech Recordings",
    author = "Celano, Giuseppe G. A.",
    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/jlcl-multiple-ingestion/2021.sigtyp-1.13/",
    doi = "10.18653/v1/2021.sigtyp-1.13",
    pages = "136--144",
    abstract = "This paper describes the model built for the SIGTYP 2021 Shared Task aimed at identifying 18 typologically different languages from speech recordings. Mel-frequency cepstral coefficients derived from audio files are transformed into spectrograms, which are then fed into a ResNet-50-based CNN architecture. The final model achieved validation and test accuracies of 0.73 and 0.53, respectively."
}