@phdthesis{wernerLappedNonuniformOrthogonal2021, title = {Lapped {{Nonuniform Orthogonal Transforms}} with {{Compact Support}}}, author = {Werner, Nils}, year = {2021}, month = jan, address = {{Erlangen}}, copyright = {All rights reserved}, file = {/Users/nwerner/Zotero/storage/2KFGVNN7/Werner_2021_Lapped Nonuniform Orthogonal Transforms with Compact Support.pdf}, keywords = {\#nosource}, school = {Friedrich-Alexander-Universit\"at Erlangen-N\"urnberg}, type = {\{\vphantom\}{{Ph}}.{{D}}.\vphantom\{\} Dissertation} } @patent{wernerPerceptualAudioCoding2019a, ids = {wernerPerceptualAudioCoding2020}, title = {Perceptual Audio Coding with Adaptive Non-Uniform Time/Frequency Tiling Using Subband Merging and the Time Domain Aliasing Reduction}, author = {Werner, Nils and Edler, Bernd and Disch, Sascha}, year = {2020}, month = apr, abstract = {Embodiments provide an audio processor for processing an audio signal to obtain a subband representation of the audio signal. The audio processor is configured to perform a cascaded lapped critically sampled transform on at least two partially overlapping blocks of samples of the audio signal, to obtain a set of subband samples on the basis of a first block of samples of the audio signal, and to obtain a corresponding set of subband samples on the basis of a second block of samples of the audio signal. Further, the audio processor is configured to perform a weighted combination of two corresponding sets of subband samples, one obtained on the basis of the first block of samples of the audio signal and one obtained on the basis on the second block of samples of the audio signal, to obtain an aliasing reduced subband representation of the audio signal; wherein performing a cascaded lapped critically sampled transform comprises segmenting a set of bins obtained on the basis of the first block of samples using at least two window functions, and to obtain at least two segmented sets of bins based on the segmented set of bins corresponding to the first block of samples; wherein performing a cascaded lapped critically sampled transform comprises segmenting a set of bins obtained on the basis of the second block of samples using the at least two window functions, and to obtain at least two sets of bins based on the segmented set of bins corresponding to the second block of samples; and wherein the sets of bins are processed using a second lapped critically sampled transform of the cascaded lapped critically sampled transform, wherein the second lapped critically sampled transform comprises performing lapped critically sampled transforms having the same framelength for at least one set of bins.}, assignee = {Fraunhofer-Gesellschaft zur F\"orderung der angewandten Forschung e.V., Friedrich-Alexander-Universit\"at Erlangen-Nuernberg}, copyright = {All rights reserved}, file = {/Users/nwerner/Zotero/storage/8WZ7KHRQ/Werner et al_2020_Perceptual audio coding with adaptive non-uniform time-frequency tiling using.pdf}, holder = {{Fraunhofer-Gesellschaft zur F\"orderung der angewandten Forschung e.V.} and {Friedrich-Alexander-Uni\hyphenate ver\hyphenate si\hyphenate t\"at Erlangen-N\"urnberg}}, keywords = {audio signal,bins,mypublication,samples,set,subband}, nationality = {WO}, number = {WO2020083727A1} } @misc{nilswernerAudiolabsRirgeneratorVersion2020, title = {Audiolabs/Rir-Generator: {{Version}} 0.1.0}, shorttitle = {Audiolabs/Rir-Generator}, author = {Nils Werner}, year = {2020}, month = oct, doi = {10.5281/zenodo.4133078}, abstract = {Initial version of the RIR Generator}, copyright = {All rights reserved}, howpublished = {Zenodo}, keywords = {\#nosource} } @patent{wernerTimeVaryingTimeFrequencyTilings2019a, title = {Time-{{Varying Time}}-{{Frequency Tilings Using Non}}-{{Uniform Orthogonal Filterbanks Based}} on {{MDCT Analysis}}/{{Synthesis}} and {{TDAR}}}, author = {Werner, Nils and Edler, Bernd}, year = {2019}, month = aug, assignee = {Fraunhofer-Gesellschaft zur F\"orderung der angewandten Forschung e.V. and Friedrich-Alexander-Universit\"at Erlangen-Nuernberg}, copyright = {All rights reserved}, holder = {{Fraunhofer-Gesellschaft zur F\"orderung der angewandten Forschung e.V.} and {Friedrich-Alexander-Universit\"at Erlangen-N\"urnberg}}, keywords = {\#nosource,mypublication}, nationality = {EU}, type = {patreqeu} } @article{wernerTimeVaryingTimeFrequencyTilings2019, title = {Time-{{Varying Time}}-{{Frequency Tilings Using Non}}-{{Uniform Orthogonal Filterbanks Based}} on {{MDCT Analysis}}/{{Synthesis}} and {{Time Domain Aliasing Reduction}}}, author = {Werner, Nils and Edler, Bernd}, year = {2019}, month = dec, volume = {26}, pages = {1783--1787}, issn = {1070-9908, 1558-2361}, doi = {10.1109/LSP.2019.2949433}, abstract = {Time Domain Aliasing Reduction (TDAR) is a method to improve the impulse response compactness of non-uniform orthogonal Modified Discrete Cosine Transforms (MDCT). Previously, TDAR was only possible between frames of identical time-frequency tilings, however in this letter we describe a method to overcome this limitation. This method enables the use of TDAR between two consecutive frames of different time-frequency tilings by introducing another subband merging or subband splitting step. Consecutively, this method allows more flexible and adaptive filterbank tilings while retaining compact impulse responses, two attributes needed for efficient perceptual audio coding.}, copyright = {All rights reserved}, file = {/Users/nwerner/Zotero/storage/SV65I49Z/Werner_Edler_2019_Time-Varying Time-Frequency Tilings Using Non-Uniform Orthogonal Filterbanks.pdf}, journal = {IEEE Signal Processing Letters}, keywords = {Frequency response,Layout,MDCT,Merging,mypublication,perceptual coding,Perceptual Coding,Switches,TDAC,TDAR,Time-domain analysis,Time-frequency analysis,time-frequency transform,Time-Frequency Transform,Transforms}, number = {12} } @inproceedings{wernerPerceptualAudioCoding2019, title = {Perceptual {{Audio Coding}} with {{Adaptive Non}}-{{Uniform Time}}/{{Frequency Tilings}} Using {{Subband Merging}} and {{Time Domain Aliasing Reduction}}}, booktitle = {Proceedings of the {{IEEE}} 2019 {{International Conference}} on {{Acoustics}}, {{Speech}} and {{Signal Processing}}}, author = {Werner, Nils and Edler, Bernd}, year = {2019}, doi = {10.1109/ICASSP.2019.8683502}, abstract = {In this paper, we investigate the coding efficiency of perceptual coding using an adaptive non-uniform orthogonal filterbank based on MDCT analysis/synthesis and time domain aliasing reduction. We compare its performance to a system using a traditional adaptive uniform MDCT filterbank with window switching. The comparison is performed using a listening test at two different quantization settings. The statistical evaluation shows that the percetpual quality of the non-uniform filterbank significantly out-performs that of the uniform filterbank by 5 to 10 MUSHRA points.}, copyright = {All rights reserved}, file = {/Users/nwerner/Zotero/storage/FDX2X57K/Werner_Edler_2019_Perceptual Audio Coding with Adaptive Non-Uniform Time-Frequency Tilings using.pdf}, keywords = {mypublication} } @inproceedings{wernerExperimentingLappedTransforms2019, ids = {werner2019experimenting}, title = {Experimenting with {{Lapped Transforms}} in {{Numerical Computation Libraries Using Polyphase Matrices}} and {{Strided Memory Views}}}, booktitle = {Proceedings of the {{Audio Engineering Society Convention}} 146}, author = {Werner, Nils and Edler, Bernd}, year = {2019}, month = mar, copyright = {All rights reserved}, file = {/Users/nwerner/Zotero/storage/YWKBNI9Y/Werner_Edler_2019_Experimenting with Lapped Transforms in Numerical Computation Libraries Using.pdf}, keywords = {mypublication} } @inproceedings{wernerComputationalComplexityNonuniform2019, title = {Computational {{Complexity}} of a {{Nonuniform Orthogonal Lapped Filterbank Based}} on {{MDCT}} and {{Time Domain Aliasing Reduction}}}, booktitle = {Proceedings of the {{Audio Engineering Society Convention}} 146}, author = {Werner, Nils and Edler, Bernd}, year = {2019}, month = mar, copyright = {All rights reserved}, file = {/Users/nwerner/Zotero/storage/VHAW7KXP/Werner_Edler_2019_Computational Complexity of a Nonuniform Orthogonal Lapped Filterbank Based on.pdf}, keywords = {mypublication} } @patent{wernerTimeDomainAliasing2018, ids = {wernerTimeDomainAliasing2018a}, title = {Time Domain Aliasing Reduction for Non-Uniform Filterbanks Which Use Spectral Analysis Followed by Partial Synthesis}, author = {Werner, Nils and Edler, Bernd}, year = {2018}, month = feb, assignee = {Fraunhofer-Gesellschaft zur F\"orderung der angewandten Forschung e.V., Friedrich-Alexander-Universit\"at Erlangen-N\"urnberg}, copyright = {All rights reserved}, file = {/Users/nwerner/Zotero/storage/AGVSYLYX/Werner_Edler_2018_Time domain aliasing reduction for non-uniform filterbanks which use spectral.pdf;/Users/nwerner/Zotero/storage/BMKATVS9/Werner_Edler_2018_Time domain aliasing reduction for non-uniform filterbanks which use spectral.pdf;/Users/nwerner/Zotero/storage/MD6Z6SQY/Werner_Edler_2018_Time domain aliasing reduction for non-uniform filterbanks which use spectral.pdf;/Users/nwerner/Zotero/storage/PXYDCXL4/Werner_Edler_2018_Time domain aliasing reduction for non-uniform filterbanks which use spectral.pdf;/Users/nwerner/Zotero/storage/Z6UXZVCG/Werner_Edler_2018_Time domain aliasing reduction for non-uniform filterbanks which use spectral.pdf;/Users/nwerner/Zotero/storage/Z7D3TZIK/Werner_Edler_2018_Time domain aliasing reduction for non-uniform filterbanks which use spectral.pdf}, holder = {{Fraunhofer-Gesellschaft zur F\"orderung der angewandten Forschung e.V.} and {Friedrich-Alexander-Universit\"at Erlangen-N\"urn\hyphenate berg}}, keywords = {audio signal,block,mypublication,samples,set,subband}, language = {en}, nationality = {WO}, number = {WO2018019909A1} } @inproceedings{wernerTrackswitchJsVersatile2017, title = {Trackswitch.Js: {{A Versatile Web}}-{{Based Audio Player}} for {{Presenting Scientific Results}}}, booktitle = {Proceedings of 3rd {{Web Audio Conference}}}, author = {Werner, Nils and Balke, Stefan and St{\"o}ter, Fabian-Robert and M{\"u}ller, Meinard and Edler, Bernd}, year = {2017}, month = aug, pages = {6}, address = {{London}}, file = {/Users/nwerner/Zotero/storage/T9SCXL78/Werner et al_2017_trackswitch.pdf}, keywords = {mypublication}, language = {en} } @article{wernerNonuniformOrthogonalFilterbanks2017, title = {Nonuniform {{Orthogonal Filterbanks Based}} on {{MDCT Analysis}}/{{Synthesis}} and {{Time}}-{{Domain Aliasing Reduction}}}, author = {Werner, Nils and Edler, Bernd}, year = {2017}, month = may, volume = {24}, pages = {589--593}, issn = {1070-9908}, doi = {10.1109/LSP.2017.2678023}, abstract = {In this letter we describe nonuniform orthogonal modified discrete cosine transform (MDCT) filterbanks and time-domain aliasing reduction (TDAR). By adding a postprocessing step to the MDCT, our method allows for arbitrary nonuniform frequency resolutions using subband merging with smooth windowing and overlap in frequency. This overlap allows for an improved temporal compactness of the impulse response, which is especially useful for audio coders. The postprocessing step comprises another lapped MDCT transform along the frequency axis and TDAR along each subband signal.}, file = {/Users/nwerner/Zotero/storage/CU6IF759/Werner_Edler_2017_Nonuniform Orthogonal Filterbanks Based on MDCT Analysis-Synthesis and.pdf}, journal = {IEEE Signal Processing Letters}, keywords = {arbitrary nonuniform frequency resolutions,audio coders,audio coding,channel bank filters,discrete cosine transforms,Encoding,frequency axis,frequency overlap,impulse response,Indexes,MDCT analysis,MDCT synthesis,Merging,Modified discrete cosine transform (MDCT),mypublication,nonuniform orthogonal filterbanks,nonuniform orthogonal modified discrete cosine transform,perceptual coding,Signal resolution,smooth windowing,subband merging,subband signal,TDAR,time-domain aliasing reduction,time-domain aliasing reduction (TDAR),time-domain analysis,Time-domain analysis,Time-frequency analysis,time-frequency transform,Transforms,transient response}, number = {5} } @misc{stoterSiSEC2016Website2016, title = {{{SiSEC}} 2016 {{Website}}}, author = {St{\"o}ter, Fabian-Robert and Werner, Nils}, year = {2016}, month = nov, doi = {10.5281/ZENODO.1490095}, abstract = {Source for SiSEC MUS 2016 Website}, copyright = {Open Access}, howpublished = {International AudioLaboratories Erlangen}, keywords = {\#nosource,mypublication-other} } @inproceedings{stoterRefiningFundamentalFrequency2015, title = {Refining Fundamental Frequency Estimates Using Time Warping}, booktitle = {Proceedings of the 2015 23rd {{European Signal Processing Conference}}}, author = {St{\"o}ter, Fabian-Robert and Werner, Nils and Bayer, Stefan and Edler, Bernd}, year = {2015}, month = aug, pages = {6--10}, doi = {10.1109/EUSIPCO.2015.7362334}, abstract = {Algorithms for estimating the fundamental frequency (F0) of a signal vary in stability and accuracy. We propose a method which iteratively improves the estimates of such algorithms by applying in each step a time warp on the input signal based on the previously estimated fundamental frequency. This time warp is designed to lead to a nearly constant F0. A refine ment is then calculated through inverse time warping of the result of an F0 estimation applied to the warped signal. The proposed refinement algorithm is not limited to specific esti mators or optimized for specific input signal characteristics. The method is evaluated on synthetic audio signals as well as speech recordings and polyphonic music recordings. Results indicate a significant improvement on accuracy when using the proposed refinement in combination with several well-known F0 estimators.}, file = {/Users/nwerner/Zotero/storage/EI6WNSRH/Stöter et al_2015_Refining fundamental frequency estimates using time warping.pdf}, keywords = {audio signal processing,Estimation,F0 estimation,F0 estimators,frequency estimation,Frequency estimation,fundamental frequency,Fundamental frequency estimation,inverse time warping,mypublication,pitch estimation,pitch tracking,polyphonic music recordings,refinement algorithm,refining fundamental frequency estimates,Robustness,Signal processing algorithms,Speech,speech recordings,speech synthesis,synthetic audio signals,time warp simulation,time warping,Time-frequency analysis} }