Attention and DCT based Global Context Modeling for Text-independent Speaker Recognition
Learning an effective speaker representation is crucial for achieving reliable performance in speaker verification tasks. Speech signals are high-dimensional, long, and variable-length sequences containing diverse information at each time-frequency (TF) location. The standard convolutional layer that operates on neighboring local regions often fails to capture the complex TF global information. Our motivation is to alleviate these challenges by increasing the modeling capacity, emphasizing significant information, and suppressing possible redundancies. We aim to design a more robust and efficient speaker recognition system by incorporating the benefits of attention mechanisms and Discrete Cosine Transform (DCT) based signal processing techniques, to effectively represent the global information in speech signals. To achieve this, we propose a general global time-frequency context modeling block for speaker modeling. First, an attention-based context model is introduced to capture the long-range and non-local relationship across different time-frequency locations. Second, a 2D-DCT based context model is proposed to improve model efficiency and examine the benefits of signal modeling. A multi-DCT attention mechanism is presented to improve modeling power with alternate DCT base forms. Finally, the global context information is used to recalibrate salient time-frequency locations by computing the similarity between the global context and local features. This effectively improves the speaker verification performance compared to the standard ResNet model and Squeeze & Excitation block by a large margin. Our experimental results show that the proposed global context modeling method can efficiently improve the learned speaker representations by achieving channel-wise and time-frequency feature recalibration.
Code (0)
등록된 구현이 없습니다.
Tasks
Speaker RecognitionSpeaker VerificationText-Independent Speaker RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning Context-Based Non-local Entropy Modeling for Image Compression
The entropy of the codes usually serves as the rate loss in the recent learned lossy image compression methods. Precise estimation of the probabilistic distribution of the codes plays a vital role in the performance. How…
Image CompressionLinear Context Transform Block
Squeeze-and-Excitation (SE) block presents a channel attention mechanism for modeling global context via explicitly capturing dependencies across channels. However, we are still far from understanding how the SE block wo…
image-classificationImage Classificationobject-detectionObject DetectionGA-NET: Global Attention Network for Point Cloud Semantic Segmentation
How to learn long-range dependencies from 3D point clouds is a challenging problem in 3D point cloud analysis. Addressing this problem, we propose a global attention network for point cloud semantic segmentation, named a…
Semantic SegmentationLong-Context Modeling via GSS-Transformer Hybrid Architecture with Learnable Mixing
Modeling long-range dependencies remains a central challenge in natural language processing. Transformer architectures achieve strong performance via self-attention but scale quadratically ($O(N^2)$) with sequence length…
Shared DIFF Transformer
DIFF Transformer improves attention allocation by enhancing focus on relevant context while suppressing noise. It introduces a differential attention mechanism that calculates the difference between two independently gen…
In-Context LearningInformation Retrieval