Explore Long-Range Context Features for Speaker Verification

Abstract

Multi-scale context information, especially long-range dependency, has shown to be beneficial for speaker verification (SV) tasks. In this paper, we propose three methods to systematically explore long-range context SV feature extraction based on ResNet and analyze their complementarity. Firstly, the Hierarchical-split block (HS-block) is introduced to enlarge the receptive fields (RFs) and extract long-range context information over the feature maps of a single layer, where the multi-channel feature maps are split into multiple groups and then stacked together. Then, by analyzing the contribution of each location of the convolution kernel to SV, we find the traditional convolution with a square kernel is not effective for long-range feature extraction. Therefore, we propose cross convolution kernel (cross-conv), which replaces the original 3 × 3 convolution kernel with a 1 × 5 and 5 × 1 convolution kernel. Cross-conv further enlarges the RFs with the same FLOPs and parameters. Finally, the Depthwise Separable Self-Attention (DSSA) module uses an explicit sparse attention strategy to capture effective long-range dependencies globally in each channel. Experiments are conducted on the VoxCeleb and CnCeleb to verify the effectiveness and robustness of the proposed system. Experimental results show that the combination of HS-block, cross-conv, and DSSA module achieves better performance than any single method, which demonstrates the complementarity of these three methods.

Branch-Transformer: A Parallel Branch Architecture to Capture Local and Global Features for Language Identification

“…The back-end scoring method then measures the similarity of linguistic representations to determine the language to which the utterance belongs. Recently, numerous studies have shown that an end-to-end approach has integrated these two stages into a single neural module [14][15][16][17][18]. A good language embedding extractor is crucial for robust and high-performance LID systems.…”

Research on an Intelligent Recommendation Method for Product Design Knowledge Based on Long- and Short-Term User Behavior Sequences

“…However, despite the temptation to assert linear sequence models as superior, properly testing for information retention from long-context tasks remains callenging. While some works have attempted to evaluate this ability through long contexts (Shaham et al, 2022;Pang et al, 2022;Dong et al, 2024;Bai et al, 2023;Li et al, 2023;Han et al, 2024), whether or not they truly require the use of long-contexts is uncertain and ascertaining long-context abilities from these tasks is difficult. This has prompted the use of more synthetic tasks (Hsieh et al, 2024), such as needle-ina-haystack (NIAH) (Kamradt, 2023) and passkey retreival (Mohtashami and Jaggi, 2023), to better control and evaluate the context sizes of models.…”

“…For example, Hsieh et al (2024) claim modern LLMs significantly over-state true context windows on a number of synthetic tasks. Meanwhile Han et al (2024) observe models to perform reasonably well on synthetic tasks, but struggle on real-world tasks, as do Li et al (2023). Hence despite a consistent trend in models behaving underwhelmingly, it remains to be understood why this occurs.…”