%Aigaion2 BibTeX export from Idiap Publications
%Friday 27 December 2024 03:44:40 AM

@INPROCEEDINGS{Juan_INTERSPEECH_2023,
         author = {Zuluaga-Gomez, Juan and Sara, Ahmed and Danielius, Visockas and Cem, Subakan},
       keywords = {automatic accent classification, Common Voice dataset, ECAPA-TDNN, SpeechBrain, wav2vec 2.0},
       projects = {Idiap, EC H2020-ROXANNE},
          title = {CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice},
      booktitle = {Proc. Interspeech 2023},
           year = {2023},
            url = {https://arxiv.org/abs/2305.18283},
       abstract = {Despite the recent advancements in Automatic Speech Recognition (ASR), the recognition of accented speech still remains a dominant problem. In order to create more inclusive ASR systems, research has shown that the integration of accent information, as part of a larger ASR framework, can lead to the mitigation of accented speech errors. We address multilingual accent classification through the ECAPA-TDNN and Wav2Vec 2.0/XLSR architectures which have been proven to perform well on a variety of speech-related downstream tasks. We introduce a simple-to-follow recipe aligned to the SpeechBrain toolkit for accent classification based on Common Voice 7.0 (English) and Common Voice 11.0 (Italian, German, and Spanish). Furthermore, we establish new state-of-the-art for English accent classification with as high as 95\% accuracy. We also study the internal categorization of the Wav2Vev 2.0 embeddings through t-SNE, noting that there is a level of clustering based on phonological similarity.},
            pdf = {https://publications.idiap.ch/attachments/papers/2023/Juan_INTERSPEECH_2023.pdf}
}