Corpus ID: 209531933

Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation

@article{Gu2020TemporalSpatialNF,
  title={Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation},
  author={R. Gu and Yuexian Zou},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.00391}
}
  • R. Gu, Yuexian Zou
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Target speech separation refers to extracting the target speaker's speech from mixed signals. Despite the recent advances in deep learning based close-talk speech separation, the applications to real-world are still an open issue. Two main challenges are the complex acoustic environment and the real-time processing requirement. To address these challenges, we propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture in reverberant… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 77 REFERENCES
    TaSNet: Time-Domain Audio Separation Network for Real-Time, Single-Channel Speech Separation
    • 134
    • PDF
    Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech Separation
    • 175
    • Highly Influential
    • PDF
    TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation.
    • 72
    • Highly Influential
    On Training Targets for Supervised Speech Separation
    • 558
    • PDF
    Supervised Speech Separation Based on Deep Learning: An Overview
    • 370
    • PDF
    Neural Spatial Filter: Target Speaker Speech Separation Assisted with Directional Information
    • 13
    • PDF
    A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation
    • 193
    • PDF
    End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction
    • 72
    • PDF
    Combining Spectral and Spatial Features for Deep Learning Based Blind Speaker Separation
    • 32
    • Highly Influential
    • PDF
    Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation
    • 92
    • Highly Influential
    • PDF