Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDGerhard Widmer
Person information
- affiliation: Johannes Kepler University of Linz, Austria
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[j50]Katharina Hoedt
, Verena Praher, Arthur Flexer, Gerhard Widmer:
Constructing adversarial examples to investigate the plausibility of explanations in deep audio and image classifiers. Neural Comput. Appl. 35(14): 10011-10029 (2023)- [j49]Silvan David Peter, Carlos Eduardo Cancino Chacón, Francesco Foscarin, Andrew McLeod, Florian Henkel, Emmanouil Karystinaios, Gerhard Widmer:
Automatic Note-Level Score-to-Performance Alignments in the ASAP Dataset. Trans. Int. Soc. Music. Inf. Retr. 6(1): 27-42 (2023) - [c212]Silvan David Peter, Carlos Eduardo Cancino Chacón, Emmanouil Karystinaios, Gerhard Widmer:
Sounding Out Reconstruction Error-Based Evaluation of Generative Models of Expressive Performance. DLfM 2023: 58-66 - [c211]Tobias Morocutti, Florian Schmid, Khaled Koutini, Gerhard Widmer:
Device-Robust Acoustic Scene Classification via Impulse Response Augmentation. EUSIPCO 2023: 176-180 - [c210]Shahed Masoudian, Khaled Koutini, Markus Schedl, Gerhard Widmer, Navid Rekabsaz:
Domain Information Control at Inference Time for Acoustic Scene Classification. EUSIPCO 2023: 181-185 - [c209]Paul Primus, Gerhard Widmer:
On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers. EUSIPCO 2023: 391-395 - [c208]Florian Schmid, Khaled Koutini, Gerhard Widmer:
Low-Complexity Audio Embedding Extractors. EUSIPCO 2023: 451-455 - [c207]Florian Schmid, Khaled Koutini, Gerhard Widmer:
Efficient Large-Scale Audio Tagging Via Transformer-to-CNN Knowledge Distillation. ICASSP 2023: 1-5 - [c206]Emmanouil Karystinaios, Francesco Foscarin, Gerhard Widmer:
Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem. IJCAI 2023: 3866-3874 - [c205]Carlos Cancino Chacón, Silvan Peter, Patricia Hu, Emmanouil Karystinaios, Florian Henkel, Francesco Foscarin, Gerhard Widmer:
The ACCompanion: Combining Reactivity, Robustness, and Musical Expressivity in an Automatic Piano Accompanist. IJCAI 2023: 5779-5787 - [c204]Matthias Plasser, Silvan Peter, Gerhard Widmer:
Discrete Diffusion Probabilistic Models for Symbolic Music Generation. IJCAI 2023: 5842-5850 - [c203]Luis Carvalho, Gerhard Widmer:
Towards Robust and Truly Large-Scale Audio-Sheet Music Retrieval. MIPR 2023: 1-6 - [c202]Luis Carvalho, Tobias Washüttl, Gerhard Widmer:
Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems. MMSys 2023: 239-248 - [i113]Shreyan Chowdhury, Gerhard Widmer:
Decoding and Visualising Intended Emotion in an Expressive Piano Performance. CoRR abs/2303.01875 (2023) - [i112]Florian Schmid, Khaled Koutini, Gerhard Widmer:
Low-Complexity Audio Embedding Extractors. CoRR abs/2303.01879 (2023) - [i111]Carlos Cancino Chacón, Silvan Peter, Patricia Hu, Emmanouil Karystinaios, Florian Henkel, Francesco Foscarin, Nimrod Varga, Gerhard Widmer:
The ACCompanion: Combining Reactivity, Robustness, and Musical Expressivity in an Automatic Piano Accompanist. CoRR abs/2304.12939 (2023) - [i110]Emmanouil Karystinaios, Francesco Foscarin, Gerhard Widmer:
Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem. CoRR abs/2304.14848 (2023) - [i109]Tobias Morocutti, Florian Schmid, Khaled Koutini, Gerhard Widmer:
Device-Robust Acoustic Scene Classification via Impulse Response Augmentation. CoRR abs/2305.07499 (2023) - [i108]Matthias Plasser, Silvan Peter, Gerhard Widmer:
Discrete Diffusion Probabilistic Models for Symbolic Music Generation. CoRR abs/2305.09489 (2023) - [i107]Shahed Masoudian, Khaled Koutini, Markus Schedl, Gerhard Widmer, Navid Rekabsaz:
Domain Information Control at Inference Time for Acoustic Scene Classification. CoRR abs/2306.08010 (2023) - [i106]Paul Primus, Gerhard Widmer:
On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers. CoRR abs/2306.11764 (2023) - [i105]Francesco Foscarin, Daniel Harasim, Gerhard Widmer:
Predicting Music Hierarchies with a Graph-Based Neural Decoder. CoRR abs/2306.16955 (2023) - [i104]Emmanouil Karystinaios, Gerhard Widmer:
Roman Numeral Analysis with Graph Neural Networks: Onset-wise Predictions from Note-wise Features. CoRR abs/2307.03544 (2023) - [i103]Paul Primus, Khaled Koutini, Gerhard Widmer:
Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets. CoRR abs/2308.04258 (2023) - [i102]Mathias Rose Bjare, Stefan Lattner, Gerhard Widmer:
Exploring Sampling Techniques for Generating Melodies with a Transformer Language Model. CoRR abs/2308.09454 (2023) - [i101]Patricia Hu, Gerhard Widmer:
The Batik-plays-Mozart Corpus: Linking Performance to Score to Musicological Annotations. CoRR abs/2309.02399 (2023) - [i100]Huan Zhang, Emmanouil Karystinaios, Simon Dixon, Gerhard Widmer, Carlos Eduardo Cancino Chacón:
Symbolic Music Representations for Classification Tasks: A Systematic Evaluation. CoRR abs/2309.02567 (2023) - [i99]Luis Carvalho, Gerhard Widmer:
Passage Summarization with Recurrent Models for Audio-Sheet Music Retrieval. CoRR abs/2309.12111 (2023) - [i98]Luis Carvalho, Tobias Washüttl, Gerhard Widmer:
Self-Supervised Contrastive Learning for Robust Audio-Sheet Music Retrieval Systems. CoRR abs/2309.12134 (2023) - [i97]Luis Carvalho, Gerhard Widmer:
Towards Robust and Truly Large-Scale Audio-Sheet Music Retrieval. CoRR abs/2309.12158 (2023) - [i96]Emmanouil Karystinaios, Francesco Foscarin, Florent Jacquemard, Masahiko Sakai, Satoshi Tojo, Gerhard Widmer:
8+8=4: Formalizing Time Units to Handle Symbolic Music Durations. CoRR abs/2310.14952 (2023) - [i95]Florian Schmid, Khaled Koutini, Gerhard Widmer:
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models. CoRR abs/2310.15648 (2023) - 2022
- [j48]Mathias Rose Bjare, Stefan Lattner, Gerhard Widmer:
Differentiable Short-Term Models for Efficient Online Learning and Prediction in Monophonic Music. Trans. Int. Soc. Music. Inf. Retr. 5(1): 190 (2022) - [c201]Paul Primus, Gerhard Widmer:
Improving Natural-Language-Based Audio Retrieval with Transfer Learning and Audio & Text Augmentations. DCASE 2022 - [c200]Florian Schmid, Shahed Masoudian, Khaled Koutini, Gerhard Widmer:
Knowledge Distillation from Transformers for Low-Complexity Acoustic Scene Classification. DCASE 2022 - [c199]Paul Primus, Gerhard Widmer:
Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers. EUSIPCO 2022: 410-413 - [c198]Khaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh, Gerhard Widmer:
Efficient Training of Audio Transformers with Patchout. INTERSPEECH 2022: 2753-2757 - [c197]Francesco Foscarin, Katharina Hoedt, Verena Praher, Arthur Flexer, Gerhard Widmer:
Concept-Based Techniques for "Musicologist-Friendly" Explanations in Deep Music Classifiers. ISMIR 2022: 876-883 - [c196]Emmanouil Karystinaios, Gerhard Widmer:
Cadence Detection in Symbolic Classical Music using Graph Neural Networks.. ISMIR 2022: 917-924 - [i94]Katharina Hoedt, Arthur Flexer, Gerhard Widmer:
Defending a Music Recommender Against Hubness-Based Adversarial Attacks. CoRR abs/2205.12032 (2022) - [i93]Carlos Cancino Chacón, Silvan David Peter, Emmanouil Karystinaios, Francesco Foscarin, Maarten Grachten, Gerhard Widmer:
Partitura: A Python Package for Symbolic Music Processing. CoRR abs/2206.01071 (2022) - [i92]Francesco Foscarin, Emmanouil Karystinaios, Silvan David Peter, Carlos Cancino Chacón, Maarten Grachten, Gerhard Widmer:
The match file format: Encoding Alignments between Scores and Performances. CoRR abs/2206.01104 (2022) - [i91]Paul Primus, Gerhard Widmer:
Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers. CoRR abs/2208.11402 (2022) - [i90]Paul Primus, Gerhard Widmer:
Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations. CoRR abs/2208.11460 (2022) - [i89]Francesco Foscarin, Katharina Hoedt, Verena Praher, Arthur Flexer, Gerhard Widmer:
Concept-Based Techniques for "Musicologist-friendly" Explanations in a Deep Music Classifier. CoRR abs/2208.12485 (2022) - [i88]Emmanouil Karystinaios, Gerhard Widmer:
Cadence Detection in Symbolic Classical Music using Graph Neural Networks. CoRR abs/2208.14819 (2022) - [i87]Florian Schmid, Khaled Koutini, Gerhard Widmer:
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation. CoRR abs/2211.04772 (2022) - [i86]Khaled Koutini, Shahed Masoudian, Florian Schmid, Hamid Eghbal-zadeh, Jan Schlüter, Gerhard Widmer:
Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers. CoRR abs/2211.13956 (2022) - [i85]Lukás Samuel Marták, Rainer Kelz, Gerhard Widmer:
Probabilistic Modelling of Signal Mixtures with Differentiable Dictionaries. CoRR abs/2211.15439 (2022) - [i84]Lukás Samuel Marták, Rainer Kelz, Gerhard Widmer:
Differentiable Dictionary Search: Integrating Linear Mixing with Deep Non-Linear Modelling for Audio Source Separation. CoRR abs/2211.15524 (2022) - 2021
- [j47]Florian Henkel, Gerhard Widmer:
Real-Time Music Following in Score Sheet Images via Multi-Resolution Prediction. Frontiers Comput. Sci. 3: 718340 (2021) - [j46]Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer:
Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks. IEEE ACM Trans. Audio Speech Lang. Process. 29: 1987-2000 (2021) - [j45]Katharina Prinz, Arthur Flexer, Gerhard Widmer:
On End-to-End White-Box Adversarial Attacks in Music Information Retrieval. Trans. Int. Soc. Music. Inf. Retr. 4(1): 93 (2021) - [c195]Alessandro B. Melchiorre, Verena Haunschmid, Markus Schedl, Gerhard Widmer:
LEMONS: Listenable Explanations for Music recOmmeNder Systems. ECIR (2) 2021: 531-536 - [c194]Florian Henkel, Gerhard Widmer:
Multi-modal Conditional Bounding Box Regression for Music Score Following. EUSIPCO 2021: 356-360 - [c193]Charles Brazier, Gerhard Widmer:
Handling Structural Mismatches in Real-time Opera Tracking. EUSIPCO 2021: 366-370 - [c192]Luis Carvalho, Gerhard Widmer:
Exploiting Temporal Dependencies for Cross-modal Music Piece Identification. EUSIPCO 2021: 386-390 - [c191]Lukás Samuel Marták, Rainer Kelz, Gerhard Widmer:
Probabilistic Modelling of Signal Mixtures with Differentiable Dictionaries. EUSIPCO 2021: 441-445 - [c190]Khaled Koutini, Shahed Masoudian, Florian Schmid, Hamid Eghbal-zadeh, Jan Schlüter, Gerhard Widmer:
Learning General Audio Representations With Large-Scale Training of Patchout Audio Transformers. HEAR@NeurIPS 2021: 65-89 - [c189]Gerhard Widmer:
Con Espressione! AI, Machine Learning, and Musical Expressivity. ICAART (1) 2021: 5 - [c188]Shreyan Chowdhury, Gerhard Widmer:
Towards Explaining Expressive Qualities in Piano Recordings: Transfer of Explanatory Features Via Acoustic Domain Adaptation. ICASSP 2021: 561-565 - [c187]Rainer Kelz, Gerhard Widmer:
Nonlinear Denoising, Linear Demixing. ICBINB@NeurIPS 2021: 54-58 - [c186]Charles Brazier, Gerhard Widmer:
On-Line Audio-to-Lyrics Alignment Based on a Reference Performance. ISMIR 2021: 66-73 - [c185]Shreyan Chowdhury, Gerhard Widmer:
On Perceived Emotion in Expressive Piano Performance: Further Experimental Evidence for the Relevance of Mid-level Perceptual Features. ISMIR 2021: 128-134 - [c184]Verena Praher, Katharina Prinz, Arthur Flexer, Gerhard Widmer:
On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples. ISMIR 2021: 531-538 - [i83]Shreyan Chowdhury, Gerhard Widmer:
Towards Explaining Expressive Qualities in Piano Recordings: Transfer of Explanatory Features via Acoustic Domain Adaptation. CoRR abs/2102.13479 (2021) - [i82]Florian Henkel, Gerhard Widmer:
Multi-modal Conditional Bounding Box Regression for Music Score Following. CoRR abs/2105.04309 (2021) - [i81]Charles Brazier, Gerhard Widmer:
Handling Structural Mismatches in Real-time Opera Tracking. CoRR abs/2105.08531 (2021) - [i80]Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer:
Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks. CoRR abs/2105.12395 (2021) - [i79]Luis Carvalho, Gerhard Widmer:
Exploiting Temporal Dependencies for Cross-Modal Music Piece Identification. CoRR abs/2105.12536 (2021) - [i78]Shreyan Chowdhury, Verena Praher, Gerhard Widmer:
Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities. CoRR abs/2106.07787 (2021) - [i77]Khaled Koutini, Hamid Eghbal-zadeh, Florian Henkel, Jan Schlüter, Gerhard Widmer:
Over-Parameterization and Generalization in Audio Classification. CoRR abs/2107.08933 (2021) - [i76]Verena Praher, Katharina Prinz, Arthur Flexer, Gerhard Widmer:
On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples. CoRR abs/2107.09045 (2021) - [i75]Shreyan Chowdhury, Gerhard Widmer:
On Perceived Emotion in Expressive Piano Performance: Further Experimental Evidence for the Relevance of Mid-level Perceptual Features. CoRR abs/2107.13231 (2021) - [i74]Charles Brazier, Gerhard Widmer:
Improving Real-time Score Following in Opera by Combining Music with Lyrics Tracking. CoRR abs/2110.02592 (2021) - [i73]Khaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh, Gerhard Widmer:
Efficient Training of Audio Transformers with Patchout. CoRR abs/2110.05069 (2021) - [i72]Florian Henkel, Stephanie Schwaiger, Gerhard Widmer:
Fully Automatic Page Turning on Real Scores. CoRR abs/2111.06643 (2021) - 2020
- [c183]Khaled Koutini, Florian Henkel, Hamid Eghbal-Zadeh, Gerhard Widmer:
Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping. DCASE 2020: 86-90 - [c182]Paul Primus, Verena Haunschmid, Patrick Praher, Gerhard Widmer:
Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples. DCASE 2020: 170-174 - [c181]Carlos Eduardo Cancino Chacón, Silvan Peter, Shreyan Chowdhury, Anna Aljanaki, Gerhard Widmer:
On the Characterization of Expressive Performance in Classical Music: First Results of the Con Espressione Game. ISMIR 2020: 613-620 - [c180]Florian Henkel, Rainer Kelz, Gerhard Widmer:
Learning to Read and Follow Music in Complete Score Sheet Images. ISMIR 2020: 780-787 - [c179]Hamid Eghbal-zadeh, Florian Henkel, Gerhard Widmer:
Context-Adaptive Reinforcement Learning using Unsupervised Learning of Context Variables. Preregister@NeurIPS 2020: 236-254 - [i71]Charles Brazier, Gerhard Widmer:
Towards Reliable Real-time Opera Tracking: Combining Alignment with Audio Event Detectors to Increase Robustness. CoRR abs/2006.11033 (2020) - [i70]David R. W. Sears, Gerhard Widmer:
Beneath (or beyond) the surface: Discovering voice-leading patterns with skip-grams. CoRR abs/2006.15399 (2020) - [i69]Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus, Verena Haunschmid, Michal Lewandowski, Werner Zellinger, Bernhard Alois Moser, Gerhard Widmer:
On Data Augmentation and Adversarial Risk: An Empirical Analysis. CoRR abs/2007.02650 (2020) - [i68]Florian Henkel, Rainer Kelz, Gerhard Widmer:
Learning to Read and Follow Music in Complete Score Sheet Images. CoRR abs/2007.10736 (2020) - [i67]Khaled Koutini, Hamid Eghbal-Zadeh, Verena Haunschmid, Paul Primus, Shreyan Chowdhury, Gerhard Widmer:
Receptive-Field Regularized CNNs for Music Classification and Tagging. CoRR abs/2007.13503 (2020) - [i66]Verena Haunschmid, Ethan Manilow, Gerhard Widmer:
audioLIME: Listenable Explanations Using Source Separation. CoRR abs/2008.00582 (2020) - [i65]Carlos Eduardo Cancino Chacón, Silvan Peter, Shreyan Chowdhury, Anna Aljanaki, Gerhard Widmer:
On the Characterization of Expressive Performance in Classical Music: First Results of the Con Espressione Game. CoRR abs/2008.02194 (2020) - [i64]Katharina Prinz, Arthur Flexer, Gerhard Widmer:
The Impact of Label Noise on a Music Tagger. CoRR abs/2008.06273 (2020) - [i63]Verena Haunschmid, Ethan Manilow, Gerhard Widmer:
Towards Musically Meaningful Explanations Using Source Separation. CoRR abs/2009.02051 (2020) - [i62]Charles Brazier, Gerhard Widmer:
Addressing the Recitative Problem in Real-time Opera Tracking. CoRR abs/2010.11013 (2020) - [i61]Paul Primus, Verena Haunschmid, Patrick Praher, Gerhard Widmer:
Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples. CoRR abs/2011.02949 (2020) - [i60]Khaled Koutini, Florian Henkel, Hamid Eghbal-zadeh, Gerhard Widmer:
Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping. CoRR abs/2011.02955 (2020)
2010 – 2019
- 2019
- [j44]Andreu Vall, Massimo Quadrana, Markus Schedl, Gerhard Widmer:
Order, context and popularity bias in next-song recommendations. Int. J. Multim. Inf. Retr. 8(2): 101-113 (2019) - [j43]Hamid Eghbal-Zadeh, Lukas Fischer, Niko Popitsch, Florian Kromp, Sabine Taschner-Mandl, Teresa Gerber, Eva Bozsaky, Peter F. Ambros, Inge M. Ambros, Gerhard Widmer, Bernhard Alois Moser:
DeepSNP: An End-to-End Deep Neural Network with Attention-Based Localization for Breakpoint Detection in Single-Nucleotide Polymorphism Array Genomic Data. J. Comput. Biol. 26(6): 572-596 (2019) - [j42]Meinard Müller, Andreas Arzt, Stefan Balke, Matthias Dorfer, Gerhard Widmer:
Cross-Modal Music Retrieval and Applications: An Overview of Key Methodologies. IEEE Signal Process. Mag. 36(1): 52-62 (2019) - [j41]Florian Henkel, Stefan Balke, Matthias Dorfer, Gerhard Widmer:
Score Following as a Multi-Modal Reinforcement Learning Problem. Trans. Int. Soc. Music. Inf. Retr. 2(1): 67-81 (2019) - [j40]Andreu Vall, Matthias Dorfer, Hamid Eghbal-zadeh, Markus Schedl, Keki Burjorjee, Gerhard Widmer:
Feature-combination hybrid recommender systems for automated music playlist continuation. User Model. User Adapt. Interact. 29(2): 527-572 (2019) - [c178]Hamid Eghbal-zadeh, Werner Zellinger, Gerhard Widmer:
Mixture Density Generative Adversarial Networks. CVPR 2019: 5820-5829 - [c177]Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer:
Receptive-Field-Regularized CNN Variants for Acoustic Scene Classification. DCASE 2019: 124-128 - [c176]Paul Primus, Hamid Eghbal-zadeh, David Eitelsebner, Khaled Koutini, Andreas Arzt, Gerhard Widmer:
Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification. DCASE 2019: 204-208 - [c175]Khaled Koutini, Hamid Eghbal-zadeh, Matthias Dorfer, Gerhard Widmer:
The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification. EUSIPCO 2019: 1-5 - [c174]Rainer Kelz, Sebastian Böck, Gerhard Widmer:
Deep Polyphonic ADSR Piano Note Transcription. ICASSP 2019: 246-250 - [c173]Stefan Balke, Matthias Dorfer, Luis Carvalho, Andreas Arzt, Gerhard Widmer:
Learning Soft-Attention Models for Tempo-invariant Audio-Sheet Music Retrieval. ISMIR 2019: 216-222 - [c172]Shreyan Chowdhury, Andreu Vall, Verena Haunschmid, Gerhard Widmer:
Towards Explainable Music Emotion Recognition: The Route via Mid-level Features. ISMIR 2019: 237-243 - [c171]Rainer Kelz, Gerhard Widmer:
Towards Interpretable Polyphonic Transcription with Invertible Neural Networks. ISMIR 2019: 376-383 - [c170]Thassilo Gadermaier, Gerhard Widmer:
A Study of Annotation and Alignment Accuracy for Performance Comparison in Complex Orchestral Music. ISMIR 2019: 769-775 - [c169]Federico Simonetta, Carlos Eduardo Cancino Chacón, Stavros Ntalampiras, Gerhard Widmer:
A Convolutional Approach to Melody Line Identification in Symbolic Scores. ISMIR 2019: 924-931 - [c168]Khaled Koutini, Shreyan Chowdhury, Verena Haunschmid, Hamid Eghbal-Zadeh, Gerhard Widmer:
Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs. MediaEval 2019 - [i59]Rainer Kelz, Sebastian Böck, Gerhard Widmer:
Multitask Learning for Polyphonic Piano Transcription, a Case Study. CoRR abs/1902.04390 (2019) - [i58]Meinard Müller, Andreas Arzt, Stefan Balke, Matthias Dorfer, Gerhard Widmer:
Cross-Modal Music Retrieval and Applications: An Overview of Key Methodologies. CoRR abs/1902.04397 (2019) - [i57]Verena Haunschmid, Shreyan Chowdhury, Gerhard Widmer:
Two-level Explanations in Music Emotion Recognition. CoRR abs/1905.11760 (2019) - [i56]Zhengshan Shi, Carlos Cancino Chacón, Gerhard Widmer:
User Curated Shaping of Expressive Performances. CoRR abs/1906.06428 (2019) - [i55]Rainer Kelz, Sebastian Böck, Gerhard Widmer:
Deep Polyphonic ADSR Piano Note Transcription. CoRR abs/1906.09165 (2019) - [i54]Federico Simonetta, Carlos Eduardo Cancino Chacón, Stavros Ntalampiras, Gerhard Widmer:
A Convolutional Approach to Melody Line Identification in Symbolic Scores. CoRR abs/1906.10547 (2019) - [i53]Stefan Balke, Matthias Dorfer, Luis Carvalho, Andreas Arzt, Gerhard Widmer:
Learning Soft-Attention Models for Tempo-invariant Audio-Sheet Music Retrieval. CoRR abs/1906.10996 (2019) - [i52]Khaled Koutini, Hamid Eghbal-zadeh, Matthias Dorfer, Gerhard Widmer:
The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification. CoRR abs/1907.01803 (2019) - [i51]Shreyan Chowdhury, Andreu Vall, Verena Haunschmid, Gerhard Widmer:
Towards Explainable Music Emotion Recognition: The Route via Mid-level Features. CoRR abs/1907.03572 (2019) - [i50]Rainer Kelz, Gerhard Widmer:
Towards Interpretable Polyphonic Transcription with Invertible Neural Networks. CoRR abs/1909.01622 (2019) - [i49]Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer:
Receptive-field-regularized CNN variants for acoustic scene classification. CoRR abs/1909.02859 (2019) - [i48]