Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks

By Yi-jiao Jiang, Deliang Wang, Runsheng Liu, Zhenming Feng. 2014

122 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Cognitive Neuroscience, 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 Biomedical Engineering

1. Emmanuel Vincent

In Cognitive Neuroscience

1. Emmanuel Vincent
2. Aditya Arie Nugraha
3. Antoine Liutkus

In Signal Processing

1. Antoine Liutkus
2. Aditya Arie Nugraha
3. Emmanuel Vincent
4. Yuki Mitsufuji
5. Naoya Takahashi
6. Shinji Watanabe
7. Jonathan Le Roux
8. John R. Hershey

Citations in the corpus

• Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising (2017, neutral): “[19] use deep neural networks (DNNs) to estimate the ideal binary mask”
• A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation (2017, unknown): “still focuses on single-channel separation using spectral cues or channel-wise filtering using ILD and ITD cues [340] or pitch and azimuth [341] (using multi-layer perceptrons).”
• Multichannel music separation with deep neural networks (2016, unknown): “Efforts on exploiting multichannel data have been done by extracting multichannel features and using them to derive a single-channel TF mask [7], [10].”
• Multichannel Audio Source Separation With Deep Neural Networks (2016, background): “Various DNN architectures and training criteria have been investigated and compared [19], [21], [22].”