Improved Rawnet With Feature Map Scaling For Text-independent Speaker Verification Using Raw Waveforms

Abstract

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

Stats

• citations76
• S2 citations—
• github stars0
• HF likes0
• heat score14.15
• arxiv keyjung2020improved

Related papers

• Rawnet: Advanced End-to-end Deep Neural Network Using Raw Waveforms For Text-independent Speaker Verification (2019)15.34
• Rawnext: Speaker Verification System For Variable-duration Utterances With Deep Layer Aggregation And Extended Dynamic Scaling Policies (2021)12.24
• Mr-rawnet: Speaker Verification System With Multiple Temporal Resolutions For Variable Duration Utterances Using Raw Waveforms (2024)2.26
• Y-vector: Multiscale Waveform Encoder For Speaker Embedding (2020)8.60
• Complementing Handcrafted Features With Raw Waveform Using A Light-weight Auxiliary Model (2021)0.00
• Rawnet: Fast End-to-end Neural Vocoder (2019)0.00
• Speech And Speaker Recognition From Raw Waveform With Sincnet (2018)0.00
• Speaker Recognition From Raw Waveform With Sincnet (2018)20.65