Speech separation remains an important topic for multi-speaker technology
researchers. Convolution augmented transformers (conformers) have performed
well for many speech processing tasks but have been under-researched for speech
separation. Most recent state-of-the-art (SOTA) separation models have been
time-domain audio separation networks (TasNets). A number of successful models
have made use of dual-path (DP) networks which sequentially process local and
global information. Time domain conformers (TD-Conformers) are an analogue of
the DP approach in that they also process local and global context sequentially
but have a different time complexity function. It is shown that for realistic
shorter signal lengths, conformers are more efficient when controlling for
feature dimension. Subsampling layers are proposed to further improve
computational efficiency. The best TD-Conformer achieves 14.6 dB and 21.2 dB
SISDR improvement on the WHAMR and WSJ0-2Mix benchmarks, respectively.

语音分离对于多说话者技术研究人员来说仍然是一个重要的课题。卷积增强变换器（conformers）在许多语音处理任务中表现良好，但在语音分离方面研究较少。最近的最新分离模型一直是时域音频分离网络（TasNets）。一些成功的模型利用了双路径（DP）网络，这些网络顺序处理本地和全局信息。时域 conformers（TD-Conformers）是 DP 方法的一种类似方式，它们也顺序处理本地和全局上下文，但时间复杂性函数不同。结果表明，在现实中较短的信号长度下，控制特征维度时 conformers 更有效。提出了子采样层以进一步提高计算效率。最佳的 TD-Conformer 在 WHAMR 和 WSJ0-2Mix 基准测试上分别实现了 14.6 dB 和 21.2 dB 的 SISDR 改进。