xLSTM-SENet: 面向单通道语音增强的xLSTM
xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
AI总结:
针对注意力架构在语音增强中序列长度扩展性不足的问题,本文提出首个基于xLSTM的单通道语音增强系统xLSTM-SENet,通过指数门控、双向性等设计,在VoiceBank+Demand数据集上匹敌或超越同复杂度的Mamba与Conformer类最优系统。
摘要:
尽管基于注意力的架构(如Conformer)在语音增强任务中表现优异,但它们面临输入序列长度可扩展性不足等挑战。相比之下,近期提出的扩展长短期记忆(Extended Long Short-Term Memory, xLSTM)架构具备线性可扩展性,但基于xLSTM的模型在语音增强领域仍未被探索。本文提出xLSTM-SENet,这是首个基于xLSTM的单通道语音增强系统。对比分析显示,在VoiceBank+Demand数据集上的语音增强任务中,xLSTM模型——甚至值得注意的是LSTM模型——在多种模型规模下均可匹敌或超越当前最优的基于Mamba和Conformer的系统。通过消融实验,我们确定了指数门控、双向性等关键架构设计选择是其有效性的来源。我们表现最佳的基于xLSTM的模型xLSTM-SENet2,在Voicebank+DEMAND数据集上超越了复杂度相近的当前最优基于Mamba和Conformer的系统。
英文摘要:
While attention-based architectures, such as Conformers, excel in speech enhancement, they face challenges such as scalability with respect to input sequence length. In contrast, the recently proposed Extended Long Short-Term Memory (xLSTM) architecture offers linear scalability. However, xLSTM-based models remain unexplored for speech enhancement. This paper introduces xLSTM-SENet, the first xLSTM-based single-channel speech enhancement system. A comparative analysis reveals that xLSTM-and notably, even LSTM-can match or outperform state-of-the-art Mamba- and Conformer-based systems across various model sizes in speech enhancement on the VoiceBank+Demand dataset. Through ablation studies, we identify key architectural design choices such as exponential gating and bidirectionality contributing to its effectiveness. Our best xLSTM-based model, xLSTM-SENet2, outperforms state-of-the-art Mamba- and Conformer-based systems of similar complexity on the Voicebank+DEMAND dataset.
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。