diff --git a/README.md b/README.md index 039c4c9..652966d 100644 --- a/README.md +++ b/README.md @@ -39,6 +39,7 @@ However, these surveys do not cover music information retrieval tasks that are i | 1989 | [Algorithms for music composition by neural nets: Improved CBR paradigms](https://quod.lib.umich.edu/cgi/p/pod/dod-idx/algorithms-for-music-composition.pdf?c=icmc;idno=bbp2372.1989.044;format=pdf) | No | | 1989 | [A connectionist approach to algorithmic composition](http://www.jstor.org/stable/3679551) | No | | 1994 | [Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multi-scale processing](http://www-labs.iro.umontreal.ca/~pift6080/H09/documents/papers/mozer-music.pdf) | No | +| 1995 | [Automatic source identification of monophonic musical instrument sounds](https://www.researchgate.net/publication/3622871_Automatic_source_identification_of_monophonic_musical_instrument_sounds) | No | | 1995 | [Neural network based model for classification of music type](http://ieeexplore.ieee.org/abstract/document/514161/) | No | | 1997 | [A machine learning approach to musical style recognition](http://repository.cmu.edu/cgi/viewcontent.cgi?article=1496&context=compsci) | No | | 1998 | [Recognition of music types](https://www.ri.cmu.edu/pub_files/pub1/soltau_hagen_1998_2/soltau_hagen_1998_2.pdf) | No | @@ -70,7 +71,7 @@ However, these surveys do not cover music information retrieval tasks that are i | 2014 | [Boundary detection in music structure analysis using convolutional neural networks](https://dav.grrrr.org/public/pub/ullrich_schlueter_grill-2014-ismir.pdf) | No | | 2014 | [Improving content-based and hybrid music recommendation using deep learning](http://www.smcnus.org/wp-content/uploads/2014/08/reco_MM14.pdf) | No | | 2014 | [A deep representation for invariance and music classification](http://www.mirlab.org/conference_papers/International_Conference/ICASSP%202014/papers/p7034-zhang.pdf) | No | -| 2015 | [Auralisation of deep convolutional neural networks: Listening to learned features](http://ismir2015.uma.es/LBD/LBD24.pdf) | [Github](https://github.com/keunwoochoi/Auralisation) | +| 2015 | [Auralisation of deep convolutional neural networks: Listening to learned features](http://ismir2015.uma.es/LBD/LBD24.pdf) | [GitHub](https://github.com/keunwoochoi/Auralisation) | | 2015 | [Downbeat tracking with multiple features and deep neural networks](http://perso.telecom-paristech.fr/~grichard/Publications/2015-durand-icassp.pdf) | No | | 2015 | [Music boundary detection using neural networks on spectrograms and self-similarity lag matrices](http://www.ofai.at/~jan.schlueter/pubs/2015_eusipco.pdf) | No | | 2015 | [Classification of spatial audio location and content using convolutional neural networks](https://www.researchgate.net/profile/Toni_Hirvonen/publication/276061831_Classification_of_Spatial_Audio_Location_and_Content_Using_Convolutional_Neural_Networks/links/5550665908ae12808b37fe5a/Classification-of-Spatial-Audio-Location-and-Content-Using-Convolutional-Neural-Networks.pdf) | No | @@ -237,11 +238,11 @@ Each entry in [dl4m.bib](dl4m.bib) also displays additional information: ## Statistics and visualisations -- 159 papers referenced. See the details in [dl4m.bib](dl4m.bib). +- 160 papers referenced. See the details in [dl4m.bib](dl4m.bib). There are more papers from 2017 than any other years combined. Number of articles per year: ![Number of articles per year](fig/articles_per_year.png) -- If you are applying DL to music, there are [327 other researchers](authors.md) in your field. +- If you are applying DL to music, there are [329 other researchers](authors.md) in your field. - 33 tasks investigated. See the list of [tasks](tasks.md). Tasks pie chart: ![Tasks pie chart](fig/pie_chart_task.png) @@ -254,7 +255,7 @@ Architectures pie chart: - 9 frameworks used. See the list of [frameworks](frameworks.md). Frameworks pie chart: ![Frameworks pie chart](fig/pie_chart_framework.png) -- Only 41 articles (25%) provide their source code. +- Only 42 articles (26%) provide their source code. Repeatability is the key to good science, so check out the [list of useful resources on reproducibility for MIR and ML](reproducibility.md). [Go back to top](https://github.com/ybayle/awesome-deep-learning-music#deep-learning-for-music-dl4m-) diff --git a/authors.md b/authors.md index a4d8b94..35fce04 100644 --- a/authors.md +++ b/authors.md @@ -124,6 +124,7 @@ - Jeong, Il-Young - Kakade, Sham M. - Kaliappan, Mala +- Kaminsky, I. - Kavcic, Alenka - Keefe, Douglas H. - Kelz, Rainer @@ -174,6 +175,7 @@ - Malik, Miroslav - Marolt, Matija - Martel Baro, Héctor +- Materka, Andrzej - Mathulaprangsan, Seksan - Matityaho, Benyamin - McFee, Brian diff --git a/dl4m.bib b/dl4m.bib index f685cc4..2514d59 100644 --- a/dl4m.bib +++ b/dl4m.bib @@ -79,6 +79,40 @@ @article{Mozer1999 year = {1994} } +@inproceedings{Kaminsky1995, + activation = {Sigmoid}, + address = {Perth, WA, Australia, Australia}, + architecture = {No}, + author = {Kaminsky, I. and Materka, Andrzej}, + batch = {No}, + booktitle = {IEEE_ICNN}, + code = {No}, + computationtime = {No}, + dataaugmentation = {No}, + dataset = {Inhouse}, + dimension = {1D}, + doi = {10.1109/ICNN.1995.488091}, + dropout = {No}, + epochs = {No}, + framework = {No}, + gpu = {No}, + input = {Raw audio}, + layers = {1}, + learningrate = {0.25}, + link = {https://www.researchgate.net/publication/3622871_Automatic_source_identification_of_monophonic_musical_instrument_sounds}, + loss = {No}, + metric = {No}, + momentum = {0.15}, + month = {Nov.}, + note = {https://ieeexplore.ieee.org/document/488091}, + optimizer = {No}, + pages = {189-194 vol.1}, + reproducible = {No}, + task = {Instrument recognition}, + title = {Automatic source identification of monophonic musical instrument sounds}, + year = {1995} +} + @inproceedings{Matityaho1995, address = {Israel}, author = {Matityaho, Benyamin and Furst, Miriam}, @@ -523,6 +557,7 @@ @inproceedings{Zhang2014 @inproceedings{Choi2015, author = {Choi, Keunwoo and Fazekas, György and Sandler, Mark Brian and Kim, Jeonghee}, booktitle = {ISMIR}, + code = {https://github.com/keunwoochoi/Auralisation}, dataset = {Inhouse}, input = {STFT}, link = {http://ismir2015.uma.es/LBD/LBD24.pdf}, diff --git a/dl4m.tsv b/dl4m.tsv index 1481c96..3384c0f 100644 --- a/dl4m.tsv +++ b/dl4m.tsv @@ -6,6 +6,7 @@ Year Entrytype Title Author Link Code Task Reproducible Dataset Framework Archit 1989 inproceedings Algorithms for music composition by neural nets: Improved CBR paradigms Lewis, J. P. https://quod.lib.umich.edu/cgi/p/pod/dod-idx/algorithms-for-music-composition.pdf?c=icmc;idno=bbp2372.1989.044;format=pdf Composition 1989 article A connectionist approach to algorithmic composition Todd, Peter M. http://www.jstor.org/stable/3679551 Composition 1994 article Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multi-scale processing Mozer, Michael C. http://www-labs.iro.umontreal.ca/~pift6080/H09/documents/papers/mozer-music.pdf Composition +1995 inproceedings Automatic source identification of monophonic musical instrument sounds Kaminsky, I. and Materka, Andrzej https://www.researchgate.net/publication/3622871_Automatic_source_identification_of_monophonic_musical_instrument_sounds No Instrument recognition No Inhouse No No No No No No Raw audio 1D Sigmoid No 0.25 No No 1995 inproceedings Neural network based model for classification of music type Matityaho, Benyamin and Furst, Miriam http://ieeexplore.ieee.org/abstract/document/514161/ MGR 1997 inproceedings A machine learning approach to musical style recognition Dannenberg, Roger B and Thom, Belinda and Watson, David http://repository.cmu.edu/cgi/viewcontent.cgi?article=1496&context=compsci MSR 1998 inproceedings Recognition of music types Soltau, Hagen and Schultz, Tanja and Westphal, Martin and Waibel, Alex https://www.ri.cmu.edu/pub_files/pub1/soltau_hagen_1998_2/soltau_hagen_1998_2.pdf No MGR No Inhouse No DNN No No No No 10x5 cepstral coefficients 2D No No No No No @@ -37,7 +38,7 @@ Year Entrytype Title Author Link Code Task Reproducible Dataset Framework Archit 2014 inproceedings Boundary detection in music structure analysis using convolutional neural networks Ullrich, Karen and Schlüter, Jan and Grill, Thomas https://dav.grrrr.org/public/pub/ullrich_schlueter_grill-2014-ismir.pdf Boundary detection [SALAMI](http://ddmal.music.mcgill.ca/research/salami/annotations) Mel-spectrogram Cross-entropy 2014 inproceedings Improving content-based and hybrid music recommendation using deep learning Wang, Xinxi and Wang, Ye http://www.smcnus.org/wp-content/uploads/2014/08/reco_MM14.pdf Recommendation [Echo Nest Taste Profile Subset](https://labrosa.ee.columbia.edu/millionsong/tasteprofile) & [7digital](https://7digital.com) Theano DBN No 15 nodes of 2 Tesla M2090 2014 inproceedings A deep representation for invariance and music classification Zhang, Chiyuan and Evangelopoulos, Georgios and Voinea, Stephen and Rosasco, Lorenzo and Poggio, Tomaso http://www.mirlab.org/conference_papers/International_Conference/ICASSP%202014/papers/p7034-zhang.pdf MGR [GTzan](http://marsyas.info/downloads/datasets.html) CNN -2015 inproceedings Auralisation of deep convolutional neural networks: Listening to learned features Choi, Keunwoo and Fazekas, György and Sandler, Mark Brian and Kim, Jeonghee http://ismir2015.uma.es/LBD/LBD24.pdf MGR Inhouse STFT +2015 inproceedings Auralisation of deep convolutional neural networks: Listening to learned features Choi, Keunwoo and Fazekas, György and Sandler, Mark Brian and Kim, Jeonghee http://ismir2015.uma.es/LBD/LBD24.pdf https://github.com/keunwoochoi/Auralisation MGR Inhouse STFT 2015 inproceedings Downbeat tracking with multiple features and deep neural networks Durand, Simon and Bello, Juan Pablo and David, Bertrand and Richard, Gaël http://perso.telecom-paristech.fr/~grichard/Publications/2015-durand-icassp.pdf Beat detection 2015 inproceedings Music boundary detection using neural networks on spectrograms and self-similarity lag matrices Grill, Thomas and Schlüter, Jan http://www.ofai.at/~jan.schlueter/pubs/2015_eusipco.pdf Boundary detection [SALAMI](http://ddmal.music.mcgill.ca/research/salami/annotations) STFT 2015 inproceedings Classification of spatial audio location and content using convolutional neural networks Hirvonen, Toni https://www.researchgate.net/profile/Toni_Hirvonen/publication/276061831_Classification_of_Spatial_Audio_Location_and_Content_Using_Convolutional_Neural_Networks/links/5550665908ae12808b37fe5a/Classification-of-Spatial-Audio-Location-and-Content-Using-Convolutional-Neural-Networks.pdf diff --git a/fig/articles_per_year.png b/fig/articles_per_year.png index 5db59bf..c5f3351 100644 Binary files a/fig/articles_per_year.png and b/fig/articles_per_year.png differ diff --git a/fig/pie_chart_architecture.png b/fig/pie_chart_architecture.png index 8dd6587..52467b6 100644 Binary files a/fig/pie_chart_architecture.png and b/fig/pie_chart_architecture.png differ diff --git a/fig/pie_chart_dataset.png b/fig/pie_chart_dataset.png index 96c3170..3723118 100644 Binary files a/fig/pie_chart_dataset.png and b/fig/pie_chart_dataset.png differ diff --git a/fig/pie_chart_framework.png b/fig/pie_chart_framework.png index b8051ce..72a607f 100644 Binary files a/fig/pie_chart_framework.png and b/fig/pie_chart_framework.png differ