Deep dilated temporal convolutional networks (TCN) have been proved to be
very effective in sequence modeling. In this paper we propose several
improvements of TCN for end-to-end approach to monaural speech separation,
which consists of 1) multi-scale dynamic weighted gated dilated convolutional
pyramids network (FurcaPy), 2) gated TCN with intra-parallel convolutional
components (FurcaPa), 3) weight-shared multi-scale gated TCN (FurcaSh), 4)
dilated TCN with gated difference-convolutional component (FurcaSu), that all
these networks take the mixed utterance of two speakers and maps it to two
separated utterances, where each utterance contains only one speaker's voice.
For the objective, we propose to train the network by directly optimizing
utterance level signal-to-distortion ratio (SDR) in a permutation invariant
training (PIT) style. Our experiments on the the public WSJ0-2mix data corpus
results in 18.4dB SDR improvement, which shows our proposed networks can leads
to performance improvement on the speaker separation task.

本文提出了几种深度卷积网络，包括多尺度动态加权门控扩展金字塔网络（FurcaPy）、带有 Intra-Parallel 卷积组件的门控 TCN（FurcaPa）、共享权重的多尺度门控 TCN（FurcaSh）以及带有门控差异卷积分量的扩张 TCN（FurcaSu）并进行了直接最优化 utterance 级别的信号失真比（SDR）的训练。在公共 WSJ0-2mix 数据语料库上进行的实验表明，这些网络提高了 18.4dB 的 SDR，显示出对演讲者分离任务性能的改进。