Divide and Conquer: A Deep CASA Approach to Talker-Independent Monaural Speaker Separation

By Yuzhou Liu, Deliang Wang. 2019

172 citations recorded by the source corpus.

We address talker-independent monaural speaker separation from the perspectives of deep learning and computational auditory scene analysis (CASA). Specifically, we decompose the multi-speaker separation task into the stages of simultaneous grouping and sequential grouping. Simultaneous grouping is first performed in each time frame by separating the spectra of different speakers with a permutation-invariantly trained neural network. In the second stage, the frame-level separated spectra are sequentially grouped to different speakers by a clustering network. The proposed deep CASA approach optimizes frame-level separation and speaker tracking in turn, and produces excellent results for both objectives. Experimental results on the benchmark WSJ0-2mix database show that the new approach achieves the state-of-the-art results with a modest model size.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yossi Adi
2. Lior Wolf
3. Eliya Nachmani
4. Zhuo Chen
5. Takuya Yoshioka
6. Yi Luo
7. Shinji Watanabe
8. Samuele Cornell

In Signal Processing

1. Yossi Adi
2. Lior Wolf
3. Eliya Nachmani
4. Zhuo Chen
5. Takuya Yoshioka
6. Yi Luo
7. Shinji Watanabe
8. Samuele Cornell

Citations in the corpus

• Voice Separation with an Unknown Number of Multiple Speakers (2020, background): “Liu & Wang (2019) suggest to use both PIT and clustering over the frame levels for speaker tracking.”
• Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation (2019, methodology): “Compared with CNN-based architectures such as temporal convolutional networks (TCNs) that only perform local modeling due to the fixed receptive fields [4, 5, 20], DPRNN is able to fully utilize global information via the inter-chunk RNNs and achieve superior performance with an even smaller model s”
• LibriMix: An Open-Source Dataset for Generalizable Speech Separation (2020, methodology): “Finally, models relying on some kind of speaker identity representation [2,6,15] cannot easily detect overfitting, since wsj0-2mix’s speakers are shared between the training and validation sets.”
• Wavesplit: End-to-End Speech Separation by Speaker Clustering (2020, unknown): “(Luo et al., 2018) 10.4 10.8 Grid LSTM PIT (Xu et al., 2018) – 10.2 ConvLSTM-GAT (Li et al., 2018) – 11.0 Chimera++ (Wang et al., 2018b) 11.5 12.0 WA-MISI-5 (Wang et al., 2018c) 12.6 13.1 blstm-TasNet (Luo & Mesgarani, 2018) 13.2 13.6 Conv-TasNet (Luo & Mesgarani, 2019) 15.3 15.6 Conv-TasNet+MBT (La”
• Attention Is All You Need In Speech Separation (2020, unknown): “The field has been revolutionized by the adoption of deep learning techniques [11–16], and with recent works [17–23] achieving impressive results by adopting an end-to-end approach.”