@inproceedings{1144,
  author = {Zhongwei Teng and Quchen Fu and Jules White and Maria Powell and Douglas Schmidt},
  title = {ARawNet: A Lightweight Solution for Leveraging Raw Waveforms in Spoof Speech Detection},
  abstract = {An emerging trend in audio processing is capturing low-level speech representations from raw waveforms. These representations have shown promising results on a variety of tasks, such as speech recognition and speech separation. Compared to handcrafted features, learning speech features via backpropagation can potentially provide the model greater flexibility in how it represents data for different tasks. However, results from empirical studies show that, in some tasks, such as spoof speech detection, handcrafted features still currently outperform learned features. Instead of evaluating handcrafted features and raw waveforms independently, this paper proposes an Auxiliary Rawnet model to complement handcrafted features with features learned from raw waveforms for spoof speech detection. A key benefit of the approach is that it can improve accuracy at a relatively low computational cost. The proposed Auxiliary Rawnet model is tested using the ASVspoof 2019 dataset and pooled EER and min-tDCF are 1.11% and 0.03645 respectively. Results from this dataset indicate that a lightweight waveform encoder can boost the performance of handcrafted-features-based encoders for 10 types of spoof attacks, including 3 challenging attacks, in exchange for a small amount of additional computational work.},
  year = {2022},
  journal = {2022 26th International Conference on Pattern Recognition (ICPR)},
  pages = {692-698},
  month = {08/2022},
  publisher = {IEEE},
  address = {Montreal, QC, Canada},
  issn = {2831-7475},
  isbn = {978-1-6654-9062-7},
  url = {https://ieeexplore.ieee.org/document/9956138},
  doi = {10.1109/ICPR56361.2022.9956138},
}