arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.06911eess.AScs.AI
收藏

异质空间融合与双维度注意力:语音增强的新范式

Heterogeneous Space Fusion and Dual-Dimension Attention: A New Paradigm for Speech Enhancement

School of Computer Science and Technology, Xinjiang University(新疆大学计算机科学与技术学院)

Tao Zheng, Liejun Wang, Yinfeng Yu

AI总结:

针对语音增强中注意力仅局限于时间维度的局限,提出融合异质空间特征、搭载双维度注意力的HFSDA框架,结合自监督嵌入与STFT特征、引入ODConv并改进Conformer,在VCTK-DEMAND数据集上性能达到SOTA水平。

摘要:

自监督学习在语音任务中已展现出优异性能,但语音增强研究领域仍有充足的提升空间。在处理语音任务时,将注意力机制仅局限于时间维度,会对有效聚焦关键语音特征造成限制。针对上述问题,本研究提出一种新型语音增强框架HFSDA,该框架巧妙融合异质空间特征,并引入双维度注意力机制,可显著提升嘈杂环境下的语音清晰度与质量。通过结合自监督学习嵌入与短时傅里叶变换(STFT)语谱图特征,我们的模型擅长同时捕捉高层语义信息与细节频谱数据,从而实现对语音信号更全面的分析与优化。此外,我们在语谱图输入分支中采用了创新的全维度动态卷积(ODConv)技术,能够增强多维度关键信息的提取与整合能力。另外,我们对Conformer模型进行了改进,不仅提升其在时间维度的特征提取能力,还增强了其在频谱域的特征提取能力。在VCTK-DEMAND数据集上开展的大量实验表明,HFSDA的性能与现有最先进模型相当,验证了我们所提方法的有效性。

英文摘要:

Self-supervised learning has demonstrated impressive performance in speech tasks, yet there remains ample opportunity for advancement in the realm of speech enhancement research. In addressing speech tasks, confining the attention mechanism solely to the temporal dimension poses limitations in effectively focusing on critical speech features. Considering the aforementioned issues, our study introduces a novel speech enhancement framework, HFSDA, which skillfully integrates heterogeneous spatial features and incorporates a dual-dimension attention mechanism to significantly enhance speech clarity and quality in noisy environments. By leveraging self-supervised learning embeddings in tandem with Short-Time Fourier Transform (STFT) spectrogram features, our model excels at capturing both high-level semantic information and detailed spectral data, enabling a more thorough analysis and refinement of speech signals. Furthermore, we employ the innovative Omni-dimensional Dynamic Convolution (ODConv) technology within the spectrogram input branch, enabling enhanced extraction and integration of crucial information across multiple dimensions. Additionally, we refine the Conformer model by enhancing its feature extraction capabilities not only in the temporal dimension but also across the spectral domain. Extensive experiments on the VCTK-DEMAND dataset show that HFSDA is comparable to existing state-of-the-art models, confirming the validity of our approach.

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。

↑