使用轻量级辅助模型用原始波形补充手工制作的特征
Complementing Handcrafted Features with Raw Waveform Using a Light-weight Auxiliary Model
摘要：
音频处理的一个新兴趋势是从原始波形中捕获低级别的语音表示。这些表示方法在诸如语音识别和语音分离等各种任务上显示出了有希望的结果。与手工制作的特征相比，通过反向传播学习语音特征在理论上为模型如何表示不同任务的数据提供了更大的灵活性。然而，从实证研究的结果表明，在某些任务，如语音欺骗检测，手工制作的功能比学习的功能更具竞争力。本文提出了一种辅助Rawnet模型，用从原始波形中学习到的特征来补充手工特征，而不是独立地评估手工特征和原始波形。该方法的一个主要优点是它可以以相对较低的计算成本提高精度。使用ASVspoof 2019数据集测试了所提出的辅助Rawnet模型，该数据集的结果表明，轻量级波形编码器可以潜在地提高基于手动特征的编码器的性能，以换取少量的额外计算工作。
英文摘要：
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 provides the model greater flexibility in how it represents data for different tasks theoretically. However, results from empirical study shows that, in some tasks, such as voice spoof detection, handcrafted features are more competitive than 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. 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 the results from this dataset indicate that a light-weight waveform encoder can potentially boost the performance of handcrafted-features-based encoders in exchange for a small amount of additional computational work.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
