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

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

Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR

Mar 01, 2022
Xuankai Chang, Niko Moritz, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux

Figure 1 for Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR

Figure 2 for Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR

Figure 3 for Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR

Figure 4 for Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR

* To appear in ICASSP2022

Access Paper or Ask Questions

(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering

Feb 18, 2022
Anoop Cherian, Chiori Hori, Tim K. Marks, Jonathan Le Roux

Figure 1 for (2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering

Figure 2 for (2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering

Figure 3 for (2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering

Figure 4 for (2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering

* Accepted at AAAI 2022 (Oral)

Access Paper or Ask Questions

Sequence Transduction with Graph-based Supervision

Nov 01, 2021
Niko Moritz, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux

Figure 1 for Sequence Transduction with Graph-based Supervision

Figure 2 for Sequence Transduction with Graph-based Supervision

Figure 3 for Sequence Transduction with Graph-based Supervision

* Submitted to IEEE ICASSP 2022

Access Paper or Ask Questions

The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks

Oct 19, 2021
Darius Petermann, Gordon Wichern, Zhong-Qiu Wang, Jonathan Le Roux

Figure 1 for The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks

Figure 2 for The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks

Figure 3 for The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks

Figure 4 for The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks

* Submitted to ICASSP2022. For resources and examples, see https://cocktail-fork.github.io

Access Paper or Ask Questions

Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy

Oct 11, 2021
Yosuke Higuchi, Niko Moritz, Jonathan Le Roux, Takaaki Hori

Figure 1 for Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy

Figure 2 for Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy

Figure 3 for Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy

* Submitted to ICASSP2022

Access Paper or Ask Questions

Visual Scene Graphs for Audio Source Separation

Sep 24, 2021
Moitreya Chatterjee, Jonathan Le Roux, Narendra Ahuja, Anoop Cherian

Figure 1 for Visual Scene Graphs for Audio Source Separation

Figure 2 for Visual Scene Graphs for Audio Source Separation

Figure 3 for Visual Scene Graphs for Audio Source Separation

Figure 4 for Visual Scene Graphs for Audio Source Separation

* Accepted at ICCV 2021

Access Paper or Ask Questions