Continuous speech separation for meeting pre-processing has recently become a focused research topic. Compared to the data in utterance-level speech separation, the meeting-style audio stream lasts longer, has an uncertain number of speakers. We adopt the time-domain speech separation method and the recently proposed Graph-PIT to build a super low-latency online speech separation model, which is very important for the real application. The low-latency time-domain encoder with a small stride leads to an extremely long feature sequence. We proposed a simple yet efficient model named Skipping Memory (SkiM) for the long sequence modeling. Experimental results show that SkiM achieves on par or even better separation performance than DPRNN. Meanwhile, the computational cost of SkiM is reduced by 75% compared to DPRNN. The strong long sequence modeling capability and low computational cost make SkiM a suitable model for online CSS applications. Our fastest real-time model gets 17.1 dB signal-to-distortion (SDR) improvement with less than 1-millisecond latency in the simulated meeting-style evaluation.
翻译:为会议预处理而持续语音分离最近已成为一个重点研究课题。 与超声层语音分离中的数据相比, 会议式的音频流持续时间较长,发言者人数不确定。 我们采用了时间- 域语音分离法和最近提议的图形- PIT, 以构建一个超低长在线语音分离模型,这对于实际应用非常重要。 低长时间- 域内编码器, 其小步引向一个非常长的特性序列。 我们为长序列建模提出了一个简单而有效的模型, 名为跳过记忆( SkiM) 。 实验结果显示, SkiM 与 DPRNN 相比, 平均或甚至更佳的分离性能实现了。 同时, SkiM 的计算成本比 DPRNN 降低了75% 。 强大的长序建模能力和低计算成本使SkiM 成为适合在线 CSS 应用程序的模型。 我们最快的实时模型获得17.1 dB 信号到扭曲(SDR) 改进, 模拟会议式评价时短于1 秒。