Darius Petermann

Native Multi-Band Audio Coding within Hyper-Autoencoded Reconstruction Propagation Networks

Mar 14, 2023
Darius Petermann, Inseon Jang, Minje Kim

Figure 2 for Native Multi-Band Audio Coding within Hyper-Autoencoded Reconstruction Propagation Networks

Figure 3 for Native Multi-Band Audio Coding within Hyper-Autoencoded Reconstruction Propagation Networks

* Accepted to ICASSP 2023. For resources and examples, see https://saige.sice.indiana.edu/research-projects/HARP-Net/

Access Paper or Ask Questions

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 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 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

SpaIn-Net: Spatially-Informed Stereophonic Music Source Separation

Feb 15, 2022
Darius Petermann, Minje Kim

Figure 2 for SpaIn-Net: Spatially-Informed Stereophonic Music Source Separation

Figure 3 for SpaIn-Net: Spatially-Informed Stereophonic Music Source Separation

Figure 4 for SpaIn-Net: Spatially-Informed Stereophonic Music Source Separation

* To Appear in Proc. ICASSP2022

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 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

HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding

Jul 23, 2021
Darius Petermann, Seungkwon Beack, Minje Kim

Figure 2 for HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding

Figure 3 for HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding

* Accepted to the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021, Mohonk Mountain House, New Paltz, NY

Access Paper or Ask Questions

HARP-Net: Hyper-Autoencoded Reconstruction Propagation\\for Scalable Neural Audio Coding

Jul 22, 2021
Darius Petermann, Seungkwon Beack, Minje Kim

$Figure 1 for HARP-Net: Hyper-Autoencoded Reconstruction Propagation\\for Scalable Neural Audio Coding$

$Figure 2 for HARP-Net: Hyper-Autoencoded Reconstruction Propagation\\for Scalable Neural Audio Coding$

$Figure 3 for HARP-Net: Hyper-Autoencoded Reconstruction Propagation\\for Scalable Neural Audio Coding$

$Figure 4 for HARP-Net: Hyper-Autoencoded Reconstruction Propagation\\for Scalable Neural Audio Coding$

* Accepted to the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021, Mohonk Mountain House, New Paltz, NY

Access Paper or Ask Questions

Deep Learning Based Source Separation Applied To Choir Ensembles

Aug 17, 2020
Darius Petermann, Pritish Chandna, Helena Cuesta, Jordi Bonada, Emilia Gomez

Figure 2 for Deep Learning Based Source Separation Applied To Choir Ensembles

Figure 3 for Deep Learning Based Source Separation Applied To Choir Ensembles

Figure 4 for Deep Learning Based Source Separation Applied To Choir Ensembles

* To appear at the 21st International Society for Music Information Retrieval Conference, Montr\'eal, Canada, 2020, audio examples available at: "https://darius522.github.io/satb-source-separation-results/"

Access Paper or Ask Questions