wehub-resource-sync
ba4be087d5
CICD NeMo / cicd-main-unit-tests (push) Blocked by required conditions
CICD NeMo / cicd-main-speech (push) Blocked by required conditions
CICD NeMo / cicd-test-container-build (push) Blocked by required conditions
CICD NeMo / cicd-import-tests (push) Blocked by required conditions
CICD NeMo / L0_Setup_Test_Data_And_Models (push) Blocked by required conditions
CICD NeMo / Nemo_CICD_Test (push) Blocked by required conditions
CICD NeMo / Coverage (e2e) (push) Blocked by required conditions
CICD NeMo / Coverage (unit-test) (push) Blocked by required conditions
CodeQL / Analyze (python) (push) Waiting to run
Create PR to main with cherry-pick from release / cherry-pick (push) Failing after 0s
CICD NeMo / pre-flight (push) Failing after 0s
CICD NeMo / configure (push) Has been skipped
Build, validate, and release Neural Modules / pre-flight (push) Failing after 1s
CICD NeMo / code-linting (push) Has been skipped
CICD NeMo / cicd-wait-in-queue (push) Waiting to run
Build, validate, and release Neural Modules / release (push) Has been skipped
Build, validate, and release Neural Modules / release-summary (push) Has been cancelled
65 lines
2.2 KiB
BibTeX
65 lines
2.2 KiB
BibTeX
@inproceedings{jukic2023flexible,
|
|
title={Flexible multichannel speech enhancement for noise-robust frontend},
|
|
author={Jukić, Ante and Balam, Jagadeesh and Ginsburg, Boris},
|
|
booktitle={Proc. WASPAA},
|
|
year={2023}
|
|
}
|
|
|
|
@inproceedings{ito2016directional,
|
|
title={Complex angular central Gaussian mixture model for directional statistics in mask-based microphone array signal processing},
|
|
author={Ito, Nobutaka and Araki, Shoko and Nakatani, Tomohiro},
|
|
booktitle={Proc. EUSIPCO},
|
|
year={2016}
|
|
}
|
|
|
|
@inproceedings{jukic2024sb,
|
|
title={Schrödinger Bridge for Generative Speech Enhancement},
|
|
author={Ante Juki\'{c} and Roman Korostik and Jagadeesh Balam and Boris Ginsburg},
|
|
year={2024},
|
|
pages={1175-1179},
|
|
booktitle={Proc. Interspeech}
|
|
}
|
|
|
|
@inproceedings{welker2022speech,
|
|
author={Simon Welker and Julius Richter and Timo Gerkmann},
|
|
title={Speech Enhancement with Score-Based Generative Models in the Complex {STFT} Domain},
|
|
year={2022},
|
|
pages={2928-2932},
|
|
booktitle={Proc. Interspeech}
|
|
}
|
|
|
|
@article{richter2023sgmse,
|
|
author = {Richter, Julius and Welker, Simon and Lemercier, Jean-Marie and Lay, Bunlong and Gerkmann, Timo},
|
|
title = {{Speech Enhancement and Dereverberation with Diffusion-Based Generative Models}},
|
|
journal = {IEEE/ACM Trans. on Audio, Speech, and Language Process.},
|
|
volume = {31},
|
|
pages = {2351-2364},
|
|
year = {2023}
|
|
}
|
|
|
|
@article{ku2024generative,
|
|
title={Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration},
|
|
author={Pin-Jui Ku and Alexander H. Liu and Roman Korostik and Sung-Feng Huang and Szu-Wei Fu and Ante Jukić},
|
|
journal={arXiv preprint arXiv:2409.16117},
|
|
year={2024},
|
|
}
|
|
|
|
@souden{souden2010,
|
|
author={Souden, Mehrez and Benesty, Jacob and Affes, SofiÈne},
|
|
journal={IEEE Transactions on Audio, Speech, and Language Processing},
|
|
title={On Optimal Frequency-Domain Multichannel Linear Filtering for Noise Reduction},
|
|
year={2010},
|
|
volume={18},
|
|
number={2},
|
|
pages={260-276}
|
|
}
|
|
|
|
@inproceedings{
|
|
lipman2023flow,
|
|
title={Flow Matching for Generative Modeling},
|
|
author={Yaron Lipman and Ricky T. Q. Chen and Heli Ben-Hamu and Maximilian Nickel and Matthew Le},
|
|
booktitle={Proc. ICLR},
|
|
year={2023},
|
|
url={https://openreview.net/forum?id=PqvMRDCJT9t}
|
|
}
|