International Audio Laboratories Erlangen

@inproceedings{nelus2021estimation,
title={Estimation of Microphone Clusters in Acoustic Sensor Networks Using Unsupervised Federated Learning},
author={Alexandru Nelus, Rene Glitza, and Rainer Martin},
booktitle={Proceedings of the {IEEE} international Conference on Acoustics, Speech, and Signal Processing ({ICASSP})},
pages={761--765},
year={2021},
organization={IEEE},
doi = {10.1109/ICASSP39728.2021.9414186}
}

@article{zhu2018admm,
title={{ADMM}-Based Sensor Network Localization Using Low-Rank Approximation},
author={Yanping Zhu, Aimin Jiang and Hon Keung Kwan},
journal={{IEEE} Sensors Journal},
volume={18},
number={20},
pages={8463--8471},
year={2018},
publisher={IEEE},
doi = {10.1109/JSEN.2018.2866686}
}

@inproceedings{subramani2021point,
title={Point Cloud Audio Processing},
author={Krishna Subramani and Paris Smaragdis},
booktitle={Proceedings of the {IEEE} Workshop on Applications of Signal Processing to Audio and Acoustics ({WASPAA})},
pages={31--35},
year={2021},
organization={IEEE},
url-pdf = {https://arxiv.org/pdf/2105.02469.pdf}
}

@inproceedings{kotti2021clock,
title={Clock-Offset and Microphone Gain Mismatch Invariant Beamforming},
author={Sofia-Eirini Kotti, Richard Heusdens, and Richard C Hendriks},
booktitle={Proceedings of the 28th European Signal Processing Conference ({EUSIPCO})},
pages={176--180},
year={2021},
organization={IEEE},
doi = {10.23919/Eusipco47968.2020.9287852},
url-pdf = {https://pure.tudelft.nl/ws/portalfiles/portal/83830242/0000176.pdf}
}

@article{hayashi2020conformer,
title={Conformer-Based ID-Aware Autoencoder for Unsupervised Anomalous Sound Detection},
author={Tomoki Hayashi, Takenori Yoshimura, and Yusuke Adachi},
journal={DCASE2020 Challenge, Tech. Rep.},
year={2020},
url-pdf = {https://dcase.community/documents/challenge2020/technical_reports/DCASE2020_Hayashi_111_t2.pdf}
}

@article{alsouda2018machine,
title={A Machine Learning Driven IoT Solution for Noise Classification in Smart Cities},
author={Yasser Alsouda, Sabri Pllana, and Arianit Kurti},
journal={arXiv preprint arXiv:1809.00238},
year={2018},
url-pdf = {https://arxiv.org/pdf/1809.00238}
}

@article{breebaart2019spatial,
author={Breebaart, Jeroen and  Cengarle, Giulio and  Lu, Lie and  Mateos, Toni and Purnhagen, Heiko and Tsingos, Nicolas},
journal={Journal of the Audio Engineering Society},
title={Spatial Coding of Complex Object-Based Program Material},
year={2019},
volume={67},
number={7/8},
pages={486-497},
doi={https://doi.org/10.17743/jaes.2018.0067},
month={July}
}

@inproceedings{9054414,
author={Kentgens, Maximilian and Behler, Andreas and Jax, Peter},
booktitle={Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})},
title={Translation of a Higher Order Ambisonics Sound Scene Based on Parametric Decomposition},
year={2020},
volume={},
number={},
pages={151-155},
doi={10.1109/ICASSP40776.2020.9054414}
}

@inproceedings{kelly20213d,
author={Kelly, Jack and Woszczyk, Wieslaw and King, Richard},
booktitle={Proceedings of the 151st Audio Engineering Society Convention},
title={3D Impulse Response Convolution With Multichannel Direct Sound: Assessing Perceptual Equivalency Between Room- and Source-Impression for Music Production},
year={2021},
month={October},
url-details={https://www.aes.org/e-lib/online/browse.cfm?elib=21496}
}

@inproceedings{nishiguchi2019spatial,
author={Nishiguchi, Masayuki and Kato, Kodai and Watanabe, Kanji and Abe, Koji and Takane, Shouichi},
booktitle={Proceedings of the 147th Audio Engineering Society Convention},
title={Spatial Auditory Masking for Three-Dimensional Audio Coding},
year={2019},
month={October},
url-details={https://www.aes.org/e-lib/browse.cfm?elib=20632}
}

@inproceedings{vandepar2019temporal,
author={van de Par, Steven and Disch, Sascha and Niedermeier, Andreas and Burdiel Pérez, Elena and Edler, Bernd},
booktitle={Proceedings of the 147th Audio Engineering Society Convention},
title={Temporal Envelope-Based Psychoacoustic Modelling for Evaluating Non-Waveform Preserving Audio Codecs},
year={2019},
month={October},
url-details={https://www.aes.org/e-lib/online/browse.cfm?elib=20686}
}

@article{DriedgerMueller16_ReviewTSM_AppliedSciences,
author  = {Jonathan Driedger and Meinard M{\"u}ller},
journal = {Applied Sciences},
title   = {A Review on Time-Scale Modification of Music Signals},
year    = {2016},
month   = {February},
volume  = {6},
number  = {2},
pages   = {57--82},
url-pdf   = {aps-w23/papers/2016_DriedgerMueller_TSMOverview_AppliedSciences_PrintedVersion.pdf}
}

@inproceedings{EwertM12_ScoreInformedNMF_ICASSP,
author     = {Sebastian Ewert and Meinard M{\"u}ller},
title      = {Using Score-Informed Constraints for {NMF}-based Source Separation},
booktitle  = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})},
address  = {Kyoto, Japan},
year       = {2012},
pages    = {129--132},
url-pdf   = {aps-w23/papers/2012_EwertMueller_ScoreConstrainedNMF_ICASSP.pdf},
url-details = {http://resources.mpi-inf.mpg.de/MIR/ICASSP2012-ScoreInformedNMF/}
}

@inproceedings{Fitzgerald10_HarmPercSep_DAFX,
author      = {Derry FitzGerald},
title       = {Harmonic/Percussive Separation Using Median Filtering},
booktitle   = {Proceedings of the International Conference on Digital Audio Effects ({DAFx})},
address     = {Graz, Austria},
year        = {2010},
pages       = {246--253},
month       = {September},
url-pdf   = {aps-w23/papers/2010_FitzGerald_HarmonicPercussiveSep_DAFx.pdf}
}

@inproceedings{StollerDE19_LyricsAlignment_ICASSP,
author    = {Daniel Stoller and Simon Durand and Sebastian Ewert},
title     = {End-To-End Lyrics Alignment for Polyphonic Music Using an Audio-To-Character Recognition Model},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})},
pages     = {181--185},
address   = {Brighton, {UK}},
year      = {2019},
url-pdf   = {aps-w23/papers/2019_StollerEwert_LyricsCTC_ICASSP_arXiv.pdf},
}

@article{Antonello2017,
author  = {N. Antonello and E. De Sena and M. Moonen and P.A. Naylor and T. van Waterschoot},
journal = {IEEE/ACM Transactions on Audio, Speech and Language Processing},
title   = {Room Impulse Response Interpolation Using a Sparse Spatio-Temporal Representation of the Sound Field},
year    = {2017},
volume  = {25},
number  = {10},
pages   = {1929--1941},
url-pdf   = {aps-w23/papers/sap_Antonello2017.pdf}
}

@article{Tervo2012,
author  = {S. Tervo and J. P\"{a}tynen and A. Kuusinen and T. Lokki,},
journal = {Journal of the Audio Engineering Society},
title   = {Spatial Decomposition Method for Room Impulse Responses},
year    = {2012},
volume  = {61},
pages   = {17--28},
url-pdf   = {aps-w23/papers/sap_Tervo2012.pdf}
}

@article{Chakrabarty2019,
author  = {S. Chakrabarty and E.A.P. Habets},
title = {Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained With Noise Signals},
journal   = {IEEE Journal of Selected Topics in Signal Processing},
year    = {2019},
month   = {March},
volume  = {13},
number  = {1},
pages   = {8--21},
url-pdf   = {aps-w23/papers/sap_Chakrabarty2019.pdf}
}

@article{Pulkki1997,
author  = {V. Pulkki},
journal = {Journal of the Audio Engineering Society},
title   = {Virtual Sound Source Positioning Using Vector Base Amplitude Panning},
year    = {1997},
month   = {June},
volume  = {45},
number  = {6},
pages   = {456--466},
url-pdf   = {aps-w23/papers/sap_Pulkki1997.pdf}
}

@inproceedings{Noisternig2003,
author  = {M. Noisternig and T. Musil and A. Sontacchi and R. Holdrich},
booktitle = {Proceedings of the International Symposium an Virtual Environments, Human-Computer Interfaces, and Measurement Systems},
title   = {3D Binaural Sound Reproduction Using a Virtual Ambisonic Approach},
pages   ={174-178},
year    = {2003},
month   = {July},
url-pdf   = {aps-w23/papers/sap_Noisternig2003.pdf}
}

@article{Adavanne2019,
author  = {S. Adavanne and A. Politis and J. Nikunen and T. Virtanen,},
journal = {IEEE Journal of Selected Topics in Signal Processing},
title   = {Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks},
year    = {2019},
month   = {March},
volume  = {13},
number  = {1},
pages   = {34--48},
url-pdf   = {aps-w23/papers/sap_Adavanne2019.pdf}
}

@article{Yoshioka2012,
author={Yoshioka, T. and Nakatani, T.},
journal={IEEE Transactions on Audio, Speech, and Language Processing},
title={Generalization of Multi-Channel Linear Prediction Methods for Blind MIMO Impulse Response Shortening},
year={2012},
volume={20},
number={10},
pages={2707-2720},
url-pdf   = {aps-w23/papers/sap_Yoshioka2012.pdf}
}

@inproceedings{schuh2016efficient,
title = {Efficient {M}ultichannel {A}udio {T}ransform {C}oding with {L}ow {D}elay and {C}omplexity},
author = {Florian Schuh and Sascha Dick and Richard Füg and Christian R. Helmrich and Nikolaus Rettelbach and Tobias Schwegler},
booktitle = {Proceedings of the 141st Audio Engineering Society Convention},
month = {Sep},
year = {2016},
url-details = {http://www.aes.org/e-lib/browse.cfm?elib=18464}
}

@inproceedings{NEURIPS2020_c5d73680,
author = {Jungil Kong and Jaehyeon Kim and Jaekyoung Bae},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {17022--17033},
publisher = {Curran Associates, Inc.},
title = {HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis},
volume = {33},
year = {2020}
}

@inproceedings{10.1145/1143844.1143891,
author = {Alex Graves and Santiago Fern\'{a}ndez and Faustino Gomez and J\"{u}rgen Schmidhuber},
title = {Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks},
year = {2006},
isbn = {1595933832},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/1143844.1143891},
doi = {10.1145/1143844.1143891},
booktitle = {Proceedings of the 23rd International Conference on Machine Learning},
pages = {369–376},
numpages = {8},
location = {Pittsburgh, Pennsylvania, USA},
series = {ICML '06}
}

@inproceedings{8683143,
author={Ryan Prenger and Rafael Valle and Bryan Catanzaro},
booktitle={Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})},
title={Waveglow: A Flow-based Generative Network for Speech Synthesis},
year={2019},
volume={},
number={},
pages={3617-3621},
doi={10.1109/ICASSP.2019.8683143}
}

@article{9444770,
author={Ning Guo and Bernd Edler},
journal={IEEE Signal Processing Letters},
title={Frequency Domain Long-Term Prediction for Low Delay General Audio Coding},
year={2021},
volume={28},
number={},
pages={1185-1189},
doi={10.1109/LSP.2021.3084503}
}

@article{10.2307/3680788,
ISSN = {01489267, 15315169},
URL = {http://www.jstor.org/stable/3680788},
author = {Xavier Serra and Julius Smith},
journal = {Computer Music Journal},
number = {4},
pages = {12--24},
publisher = {The MIT Press},
title = {Spectral Modeling Synthesis: A Sound Analysis/Synthesis System Based on a Deterministic Plus Stochastic Decomposition},
urldate = {2022-08-16},
volume = {14},
year = {1990}
}