Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for John R. Hershey

John R. Hershey

Distance-Based Sound Separation

Jul 01, 2022
Katharine Patterson, Kevin Wilson, Scott Wisdom, John R. Hershey

Figure 1 for Distance-Based Sound Separation

Figure 2 for Distance-Based Sound Separation

Figure 3 for Distance-Based Sound Separation

Figure 4 for Distance-Based Sound Separation

* Accepted for publication at Interspeech 2022

Access Paper or Ask Questions

CycleGAN-Based Unpaired Speech Dereverberation

Mar 29, 2022
Hannah Muckenhirn, Aleksandr Safin, Hakan Erdogan, Felix de Chaumont Quitry, Marco Tagliasacchi, Scott Wisdom, John R. Hershey

Figure 1 for CycleGAN-Based Unpaired Speech Dereverberation

Figure 2 for CycleGAN-Based Unpaired Speech Dereverberation

Figure 3 for CycleGAN-Based Unpaired Speech Dereverberation

* Submitted to Interspeech 2022

Access Paper or Ask Questions

Adapting Speech Separation to Real-World Meetings Using Mixture Invariant Training

Oct 20, 2021
Aswin Sivaraman, Scott Wisdom, Hakan Erdogan, John R. Hershey

Figure 1 for Adapting Speech Separation to Real-World Meetings Using Mixture Invariant Training

Figure 2 for Adapting Speech Separation to Real-World Meetings Using Mixture Invariant Training

Access Paper or Ask Questions

Improving Bird Classification with Unsupervised Sound Separation

Oct 07, 2021
Tom Denton, Scott Wisdom, John R. Hershey

Figure 1 for Improving Bird Classification with Unsupervised Sound Separation

Figure 2 for Improving Bird Classification with Unsupervised Sound Separation

Figure 3 for Improving Bird Classification with Unsupervised Sound Separation

Figure 4 for Improving Bird Classification with Unsupervised Sound Separation

* 5 pages, 3 figures. Examples available at https://bird-mixit.github.io

Access Paper or Ask Questions

DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement

Jun 30, 2021
Yuma Koizumi, Shigeki Karita, Scott Wisdom, Hakan Erdogan, John R. Hershey, Llion Jones, Michiel Bacchiani

Figure 1 for DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement

Figure 2 for DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement

Figure 3 for DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement

Figure 4 for DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement

* 5 pages, 2 figure. submitted to WASPAA 2021

Access Paper or Ask Questions

Sparse, Efficient, and Semantic Mixture Invariant Training: Taming In-the-Wild Unsupervised Sound Separation

Jun 01, 2021
Scott Wisdom, Aren Jansen, Ron J. Weiss, Hakan Erdogan, John R. Hershey

Figure 1 for Sparse, Efficient, and Semantic Mixture Invariant Training: Taming In-the-Wild Unsupervised Sound Separation

Figure 2 for Sparse, Efficient, and Semantic Mixture Invariant Training: Taming In-the-Wild Unsupervised Sound Separation

* 5 pages, 1 figure. submitted to WASPAA 2021

Access Paper or Ask Questions

End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings

May 05, 2021
Soumi Maiti, Hakan Erdogan, Kevin Wilson, Scott Wisdom, Shinji Watanabe, John R. Hershey

Figure 1 for End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings

Figure 2 for End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings

Figure 3 for End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings

Figure 4 for End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings

* ICASSP 2021, SPE-54.1
* 5 pages, 2 figures, ICASSP 2021

Access Paper or Ask Questions