@inproceedings{yadavalli-etal-2022-exploring,
    title = "Exploring the Effect of Dialect Mismatched Language Models in {T}elugu Automatic Speech Recognition",
    author = "Yadavalli, Aditya  and
      Mirishkar, Ganesh Sai  and
      Vuppala, Anil",
    editor = "Ippolito, Daphne  and
      Li, Liunian Harold  and
      Pacheco, Maria Leonor  and
      Chen, Danqi  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop",
    month = jul,
    year = "2022",
    address = "Hybrid: Seattle, Washington + Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.naacl-srw.36/",
    doi = "10.18653/v1/2022.naacl-srw.36",
    pages = "292--301",
    abstract = "Previous research has found that Acoustic Models (AM) of an Automatic Speech Recognition (ASR) system are susceptible to dialect variations within a language, thereby adversely affecting the ASR. To counter this, researchers have proposed to build a dialect-specific AM while keeping the Language Model (LM) constant for all the dialects. This study explores the effect of dialect mismatched LM by considering three different Telugu regional dialects: Telangana, Coastal Andhra, and Rayalaseema. We show that dialect variations that surface in the form of a different lexicon, grammar, and occasionally semantics can significantly degrade the performance of the LM under mismatched conditions. Therefore, this degradation has an adverse effect on the ASR even when dialect-specific AM is used. We show a degradation of up to 13.13 perplexity points when LM is used under mismatched conditions. Furthermore, we show a degradation of over 9{\%} and over 15{\%} in Character Error Rate (CER) and Word Error Rate (WER), respectively, in the ASR systems when using mismatched LMs over matched LMs."
}