Deep attractor network for single-microphone speaker separation

@article{Chen2017DeepAN,
  title={Deep attractor network for single-microphone speaker separation},
  author={Zhuo Chen and Yi Luo and Nima Mesgarani},
  journal={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2017},
  pages={246-250}
}
Highlight Information
Despite the overwhelming success of deep learning in various speech processing tasks, the problem of separating simultaneous speakers in a mixture remains challenging. [...] Key Method Attractor points in this study are created by finding the centroids of the sources in the embedding space, which are subsequently used to determine the similarity of each bin in the mixture to each source. The network is then trained to minimize the reconstruction error of each source by optimizing the embeddings.Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 151 CITATIONS

Practical applicability of deep neural networks for overlapping speaker separation

VIEW 9 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Which Ones Are Speaking? Speaker-Inferred Model for Multi-Talker Speech Separation

VIEW 13 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Multi-speakers Speech Separation Based on Modified Attractor Points Estimation and GMM Clustering

VIEW 14 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Retrieving Signals with Deep Complex Extractors

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Deep Attractor Networks for Speaker Re-Identification and Blind Source Separation

VIEW 8 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Generalization Challenges for Neural Architectures in Audio Source Separation.

VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Single Channel Speech Separation with Constrained Utterance Level Permutation Invariant Training Using Grid LSTM

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2020

CITATION STATISTICS

  • 21 Highly Influenced Citations

  • Averaged 47 Citations per year from 2017 through 2019

  • 43% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 17 REFERENCES

Permutation invariant training of deep models for speaker-independent multi-talker speech separation

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Deep clustering: Discriminative embeddings for segmentation and separation

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Acoustic modelling with CD-CTC-SMBR LSTM RNNS

VIEW 1 EXCERPT

The MERL/SRI system for the 3RD CHiME challenge using beamforming, robust feature extraction, and advanced speech recognition

VIEW 2 EXCERPTS