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

Add to Chrome

Add to Firefox

Picture for Jonathan Le Roux

Jonathan Le Roux

Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks

Dec 14, 2022
Darius Petermann, Gordon Wichern, Aswin Shanmugam Subramanian, Zhong-Qiu Wang, Jonathan Le Roux

Figure 1 for Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks

Figure 2 for Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks

Figure 3 for Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks

Figure 4 for Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks

* Submitted to IEEE TASLP (In review), 13 pages, 6 figures

Access Paper or Ask Questions

Hyperbolic Audio Source Separation

Dec 09, 2022
Darius Petermann, Gordon Wichern, Aswin Subramanian, Jonathan Le Roux

Figure 1 for Hyperbolic Audio Source Separation

Figure 2 for Hyperbolic Audio Source Separation

Figure 3 for Hyperbolic Audio Source Separation

Figure 4 for Hyperbolic Audio Source Separation

* Submitted to ICASSP 2023, Demo page: https://darius522.github.io/hyperbolic-audio-sep/

Access Paper or Ask Questions

Reverberation as Supervision for Speech Separation

Nov 15, 2022
Rohith Aralikatti, Christoph Boeddeker, Gordon Wichern, Aswin Shanmugam Subramanian, Jonathan Le Roux

Figure 1 for Reverberation as Supervision for Speech Separation

Figure 2 for Reverberation as Supervision for Speech Separation

Figure 3 for Reverberation as Supervision for Speech Separation

Figure 4 for Reverberation as Supervision for Speech Separation

* 5 pages, 2 figures, 4 tables. Submitted to ICASSP 2023

Access Paper or Ask Questions

Optimal Condition Training for Target Source Separation

Nov 11, 2022
Efthymios Tzinis, Gordon Wichern, Paris Smaragdis, Jonathan Le Roux

Figure 1 for Optimal Condition Training for Target Source Separation

Figure 2 for Optimal Condition Training for Target Source Separation

Figure 3 for Optimal Condition Training for Target Source Separation

* Submitted to ICASSP 2023

Access Paper or Ask Questions

Cold Diffusion for Speech Enhancement

Nov 04, 2022
Hao Yen, François G. Germain, Gordon Wichern, Jonathan Le Roux

Figure 1 for Cold Diffusion for Speech Enhancement

Figure 2 for Cold Diffusion for Speech Enhancement

* 5 pages, 1 figure, 1 table, 3 algorithms. Submitted to ICASSP 2023

Access Paper or Ask Questions

Towards End-to-end Speaker Diarization in the Wild

Nov 02, 2022
Zexu Pan, Gordon Wichern, François G. Germain, Aswin Subramanian, Jonathan Le Roux

Figure 1 for Towards End-to-end Speaker Diarization in the Wild

Figure 2 for Towards End-to-end Speaker Diarization in the Wild

Figure 3 for Towards End-to-end Speaker Diarization in the Wild

Figure 4 for Towards End-to-end Speaker Diarization in the Wild

* 5 pages, 2 figures, 2 tables. Submitted to ICASSP 2023

Access Paper or Ask Questions

Heterogeneous Target Speech Separation

Apr 07, 2022
Efthymios Tzinis, Gordon Wichern, Aswin Subramanian, Paris Smaragdis, Jonathan Le Roux

Figure 1 for Heterogeneous Target Speech Separation

Figure 2 for Heterogeneous Target Speech Separation

Figure 3 for Heterogeneous Target Speech Separation

Figure 4 for Heterogeneous Target Speech Separation

* Submitted to Interspeech 2022

Access Paper or Ask Questions

Locate This, Not That: Class-Conditioned Sound Event DOA Estimation

Mar 08, 2022
Olga Slizovskaia, Gordon Wichern, Zhong-Qiu Wang, Jonathan Le Roux

Figure 1 for Locate This, Not That: Class-Conditioned Sound Event DOA Estimation

Figure 2 for Locate This, Not That: Class-Conditioned Sound Event DOA Estimation

Figure 3 for Locate This, Not That: Class-Conditioned Sound Event DOA Estimation

Figure 4 for Locate This, Not That: Class-Conditioned Sound Event DOA Estimation

* Accepted for publication at ICASSP 2022

Access Paper or Ask Questions