Improved RawNet with Filter-wise Rescaling for Text-independent Speaker Verification using Raw Waveforms

By Jee-weon Jung, Seung-bin Kim, Hye-jin Shim, Ju-ho Kim, Ha-jin Yu. 2020

60 citations recorded by the source corpus.

Recent advances in deep learning have facilitated the design of speaker verification systems that directly input raw waveforms. For example, RawNet extracts speaker embeddings from raw waveforms, which simplifies the process pipeline and demonstrates competitive performance. In this study, we improve RawNet by scaling feature maps using various methods. The proposed mechanism utilizes a scale vector that adopts a sigmoid non-linear function. It refers to a vector with dimensionality equal to the number of filters in a given feature map. Using a scale vector, we propose to scale the feature map multiplicatively, additively, or both. In addition, we investigate replacing the first convolution layer with the sinc-convolution layer of SincNet. Experiments performed on the VoxCeleb1 evaluation dataset demonstrate the effectiveness of the proposed methods, and the best performing system reduces the equal error rate by half compared to the original RawNet. Expanded evaluation results obtained using the VoxCeleb1-E and VoxCeleb-H protocols marginally outperform existing state-of-the-art systems.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Icassp 2022 Deep Noise Suppression Challenge (2022, methodology): “The baseline speaker embedding extractor is RawNet2 [16] trained on wideband audio from VoxCeleb2 [17].”
ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild (2022, methodology): “Originating from [39] and based on RawNet [40] and graph attention networks, AASIST [41] is representative of progress in the use of E2E architectures.”
Speaker recognition based on deep learning: An overview (2020, background): “They also made several improvements to the original raw wave network [56, 57, 104] which results in excellent performance.”
End-to-End anti-spoofing with RawNet2 (2020, methodology): “This section describes modifications made to the original RawNet2 architecture [7] so that it can be applied successfully to anti-spoofing.”