%Aigaion2 BibTeX export from Idiap Publications
%Wednesday 08 May 2024 02:28:10 PM

@INPROCEEDINGS{Khosravani_ASRU-2_2021,
         author = {Khosravani, Abbas and Garner, Philip N. and Lazaridis, Alexandros},
       keywords = {Automatic Speech Recognition, benchmarks, Code-Switching, German, Multilingual},
       projects = {Idiap},
          month = dec,
          title = {An Evaluation Benchmark for Automatic Speech Recognition of German-English Code-Switching},
      booktitle = {IEEE Automatic Speech Recognition and Understanding Workshop},
           year = {2021},
       abstract = {Code-switching arises when a (typically multilingual) speaker changes language during an utterance. This linguistic phenomenon causes problems for automatic speech recognition as the models are typically monolingual. In this work, we present a code-switching evaluation scenario for German-English that is created by resegmenting the German Spoken Wikipedia Corpus. Since these articles span a wide variety of (often technical) topics, they include a lot of borrowing and code-switching phenomena. The resulting corpus consists of around 34 hours of intra-sentential switches. We investigate end-to-end approaches using both monolingual and multilingual automatic speech recognition as well as language modeling to address the code-switching scenario. Results suggest that multilingual sequence-to-sequence approaches are to be preferred for code-switching thanks to the power of the attention mechanism. The segments are made available to the community as a benchmark.},
            pdf = {https://publications.idiap.ch/attachments/papers/2022/Khosravani_ASRU-2_2021.pdf}
}