论文标题
在混响环境中探索具有两流架构的时域深度吸引力网络
Exploring the time-domain deep attractor network with two-stream architectures in a reverberant environment
论文作者
论文摘要
深度吸引者网络（DAN）用歧视性嵌入和说话者吸引者进行语音分离。与基于置换不变训练（PIT）的方法相比，DAN定义了一个深层嵌入空间，并在每个时间频率（T-F）箱中提供了更精细的表示。但是，已经观察到，如果直接部署在混响环境中，DAN的信号质量的改善有限。在清洁混合物语音上取得了时间域分离网络的成功之后，我们提出了一个带有两条卷积网络的时间域DAN（TD-DAN），在可变数量的扬声器数量的条件下，这些卷积网络有效地执行了替代和分离任务。 TD-DAN的编码流（SES）的扬声器经过训练，可以对嵌入式空间中的扬声器信息进行建模。语音解码流（SDS）接受SES中的说话者吸引者，并学会从光谱时代的表示中估算早期反思。同时，使用其他聚类损失来弥合甲骨文和估计吸引子之间的差距。实验是在空间化的多演讲者华尔街日报（SMS-WSJ）数据集上进行的。将早期反射与态和回响信号进行了比较，然后选择作为学习目标。实验结果表明，TD-DAN在Reverberant 2/3-Speaker评估集上达到了9.79/7.47 dB的规模不变源与启动比（SI-SDR），超过了1.92/0.68 DB和0.91/0.91/0.91/0.91/0.91/0.91/0.91/0.91/0.91/0.91/0.91/0.47 db，超过了基线DAN和基线时间域和卷积时间域的音频分离网络（CORV-TASNET）。
Deep attractor networks (DANs) perform speech separation with discriminative embeddings and speaker attractors. Compared with methods based on the permutation invariant training (PIT), DANs define a deep embedding space and deliver a more elaborate representation on each time-frequency (T-F) bin. However, it has been observed that the DANs achieve limited improvement on the signal quality if directly deployed in a reverberant environment. Following the success of time-domain separation networks on the clean mixture speech, we propose a time-domain DAN (TD-DAN) with two-streams of convolutional networks, which efficiently perform both dereverberation and separation tasks under the condition of a variable number of speakers. The speaker encoding stream (SES) of the TD-DAN is trained to model the speaker information in the embedding space. The speech decoding stream (SDS) accepts speaker attractors from the SES and learns to estimate early reflections from the spectro-temporal representations. Meanwhile, additional clustering losses are used to bridge the gap between the oracle and the estimated attractors. Experiments were conducted on the Spatialized Multi-Speaker Wall Street Journal (SMS-WSJ) dataset. The early reflection was compared with the anechoic and reverberant signals and then was chosen as the learning targets. The experimental results demonstrated that the TD-DAN achieved scale-invariant source-to-distortion ratio (SI-SDR) gains of 9.79/7.47 dB on the reverberant 2/3-speaker evaluation set, exceeding the baseline DAN and convolutional time-domain audio separation network (Conv-TasNet) by 1.92/0.68 dB and 0.91/0.47 dB, respectively.
