Add Brunner2017

ybayle · Nov 24, 2017 · 4d8271a · 4d8271a
1 parent b50600c
commit 4d8271a
Show file tree

Hide file tree

Showing 13 changed files with 44 additions and 10 deletions.
diff --git a/README.md b/README.md
@@ -31,6 +31,7 @@ However, these surveys do not cover music information retrieval tasks that are i
 | [Vision-based detection of acoustic timed events: A case study on clarinet note onsets](http://dorienherremans.com/dlm2017/papers/bazzica2017clarinet.pdf) | No |
 | Neural net modeling of music | No |
 | [Deep learning techniques for music generation - A survey](https://arxiv.org/pdf/1709.01620.pdf) | No |
+| [JamBot: Music theory aware chord based generation of polyphonic music with LSTMs](https://arxiv.org/pdf/1711.07682.pdf) | [GitHub](https://github.com/brunnergino/JamBot) |
 | [A supervised learning approach to musical style recognition](https://www.researchgate.net/profile/Giuseppe_Buzzanca/publication/228588086_A_supervised_learning_approach_to_musical_style_recognition/links/54b43ee90cf26833efd0109f.pdf) | No |
 | [XFlow: 1D <-> 2D cross-modal deep neural networks for audiovisual classification](https://arxiv.org/pdf/1709.00572.pdf) | No |
 | [Machine listening intelligence](http://dorienherremans.com/dlm2017/papers/cella2017mli.pdf) | No |
@@ -223,23 +224,24 @@ Each entry in [dl4m.bib](dl4m.bib) also displays additional information:
 
 ## Statistics and visualisations
 
-- 154 papers referenced. See the details in [dl4m.bib](dl4m.bib).
-- If you are applying DL to music, there are [319 other researchers](authors.md) in your field.
+- 155 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 [323 other researchers](authors.md) in your field.
 - 31 tasks investigated. See the list of [tasks](tasks.md).
 Tasks pie chart:
 ![Tasks pie chart](fig/pie_chart_task.png)
-- 42 datasets used. See the list of [datasets](datasets.md).
+- 43 datasets used. See the list of [datasets](datasets.md).
 Datasets pie chart:
 ![Datasets pie chart](fig/pie_chart_dataset.png)
 - 25 architectures used. See the list of [architectures](architectures.md).
 Architectures pie chart:
 ![Architectures pie chart](fig/pie_chart_architecture.png)
-- 7 frameworks used. See the list of [frameworks](frameworks.md).
+- 8 frameworks used. See the list of [frameworks](frameworks.md).
 Frameworks pie chart:
 ![Frameworks pie chart](fig/pie_chart_framework.png)
-- Number of articles per year:
-![Number of articles per year](fig/articles_per_year.png)
-- Only 38 articles (24%) provide their source code.
+- Only 39 articles (25%) 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
@@ -19,6 +19,7 @@
 - Brakel, Philémon
 - Bransen, Jeroen
 - Briot, Jean-Pierre
+- Brunner, Gino
 - Buzzanca, Giuseppe
 - Böck, Sebastian
 - Cai, Lianhong
@@ -290,13 +291,16 @@
 - Wang, Wenwu
 - Wang, Xinxi
 - Wang, Ye
+- Wang, Yuyi
 - Wang, Ziyuan
 - Watson, David
+- Wattenhofer, Roger
 - Weiss, Ron J.
 - Weninger, Felix
 - Wenwu Wang
 - Weyde, Tillman
 - Widmer, Gerhard
+- Wiesendanger, Jonas
 - Wilson, Kevin
 - Wu, Chung-Hsien
 - Wu, Raymond

diff --git a/datasets.md b/datasets.md
@@ -25,6 +25,7 @@ Please refer to the list of useful acronyms used in deep learning and music: [ac
 - [Jamendo](http://www.mathieuramona.com/wp/data/jamendo/)
 - [LMD](https://sites.google.com/site/carlossillajr/resources/the-latin-music-database-lmd)
 - [LabROSA](http://labrosa.ee.columbia.edu/projects/melody/)
+- [Lakh MIDI](https://labrosa.ee.columbia.edu/sounds/music/)
 - [Last.fm](https://www.last.fm/)
 - [LyricFind](http://lyricfind.com/)
 - [MAPS](http://www.tsi.telecom-paristech.fr/aao/en/2010/07/08/maps-database-a-piano-database-for-multipitch-estimation-and-automatic-transcription-of-music/)

diff --git a/dl4m.bib b/dl4m.bib
@@ -46,6 +46,30 @@ @unpublished{Briot2017
   year = {2017}
 }
 
+@inproceedings{Brunner2017,
+  activation = {Softmax},
+  address = {Boston, MA, USA},
+  architecture = {RNN-LSTM},
+  author = {Brunner, Gino and Wang, Yuyi and Wattenhofer, Roger and Wiesendanger, Jonas},
+  batch = {No},
+  booktitle = {[IEEE_ICTAI](http://ictai2017.org/)},
+  code = {https://github.com/brunnergino/JamBot},
+  dataaugmentation = {No},
+  dataset = {[Lakh MIDI](https://labrosa.ee.columbia.edu/sounds/music/)},
+  dropout = {No},
+  epochs = {4},
+  framework = {Keras-TensorFlow},
+  gpu = {1},
+  learningrate = {0.00001},
+  link = {https://arxiv.org/pdf/1711.07682.pdf},
+  month = {Nov.},
+  optimizer = {Adam},
+  pages = {1--8},
+  task = {Composition},
+  title = {JamBot: Music theory aware chord based generation of polyphonic music with LSTMs},
+  year = {2017}
+}
+
 @inproceedings{Buzzanca2002,
   author = {Buzzanca, Giuseppe},
   booktitle = {Music and Artificial Intelligence. Additional Proceedings of the Second International Conference, ICMAI},
@@ -681,7 +705,7 @@ @inproceedings{Koutini2017
 }
 
 @unpublished{Kum2017,
-  activation = {Leakey ReLU},
+  activation = {Leaky ReLU},
   architecture = {CNN},
   author = {Kum, Sangeun and Nam, Juhan},
   batch = {No},

diff --git a/dl4m.py b/dl4m.py
@@ -235,7 +235,7 @@ def my_autopct(pct):
     return my_autopct
 
 
-def pie_chart(items, field_name, max_nb_slice=7):
+def pie_chart(items, field_name, max_nb_slice=8):
     """Description of pie_chart
     Display a pie_chart from the items given in input
     """

diff --git a/dl4m.tsv b/dl4m.tsv
@@ -4,6 +4,7 @@ Year	Entrytype	Title	Author	Link	Code	Task	Reproducible	Dataset	Framework	Archit
 2017	inproceedings	Vision-based detection of acoustic timed events: A case study on clarinet note onsets	Bazzica, Alessio and Van Gemert, JC and Liem, CCS and Hanjalic, A	http://dorienherremans.com/dlm2017/papers/bazzica2017clarinet.pdf		Onset detection		[C4S](http://mmc.tudelft.nl/users/alessio-bazzica#C4S-dataset)		CNN												
 1988	inproceedings	Neural net modeling of music	Bharucha, J.																			
 2017	unpublished	Deep learning techniques for music generation - A survey	Briot, Jean-Pierre and Hadjeres, Gaëtan and Pachet, François	https://arxiv.org/pdf/1709.01620.pdf																		
+2017	inproceedings	JamBot: Music theory aware chord based generation of polyphonic music with LSTMs	Brunner, Gino and Wang, Yuyi and Wattenhofer, Roger and Wiesendanger, Jonas	https://arxiv.org/pdf/1711.07682.pdf	https://github.com/brunnergino/JamBot	Composition		[Lakh MIDI](https://labrosa.ee.columbia.edu/sounds/music/)	Keras-TensorFlow	RNN-LSTM	No	No	4	No			Softmax		0.00001	Adam	1	
 2002	inproceedings	A supervised learning approach to musical style recognition	Buzzanca, Giuseppe	https://www.researchgate.net/profile/Giuseppe_Buzzanca/publication/228588086_A_supervised_learning_approach_to_musical_style_recognition/links/54b43ee90cf26833efd0109f.pdf		MGR																
 2017	unpublished	XFlow: 1D <-> 2D cross-modal deep neural networks for audiovisual classification	Cangea, Cătălina and Veličković, Petar and Liò, Pietro	https://arxiv.org/pdf/1709.00572.pdf																		
 2017	inproceedings	Machine listening intelligence	Cella, Carmine-Emanuele	http://dorienherremans.com/dlm2017/papers/cella2017mli.pdf																		
@@ -62,7 +63,7 @@ Year	Entrytype	Title	Author	Link	Code	Task	Reproducible	Dataset	Framework	Archit
 2016	inproceedings	A fully convolutional deep auditory model for musical chord recognition	Korzeniowski, Filip and Widmer, Gerhard	https://www.researchgate.net/profile/Filip_Korzeniowski/publication/305590295_A_Fully_Convolutional_Deep_Auditory_Model_for_Musical_Chord_Recognition/links/579486ba08aed51475cc6958/A-Fully-Convolutional-Deep-Auditory-Model-for-Musical-Chord-Recognition.pdf?_iepl%5BhomeFeedViewId%5D=HTzFFmKPia2YminQ4psHT5at&_iepl%5Bcontexts%5D%5B0%5D=pcfhf&_iepl%5BinteractionType%5D=publicationDownload&origin=publication_detail&ev=pub_int_prw_xdl&msrp=Dz_6LKHzYcPyP-LmgZPF-m63ayZ6k0entFEntooiu_e32zfETNQXKPQSTFOI87NONIIQuUQdnUtwORdomTXfteTrb09KiAIdDtBJnw_02P6JeRr5zu2eyaCG.2Uxsi_eENxtbYL39lvorIK8LofRYhkgpUHzpzmVzkIEiyHc0wUY87rEa4PH1qbXi4k4RyagHUsA2IsZtewnprglORjx2v9Cwbk9ZfQ.cd67BaqtHul_hE6SX6vUFKuldz81aH6dWq-cYMkq5vQKCHcvB8l9zgeM694Efb_r2wBB5GT9idt3OLeME0UxVHI6ROxamgK3LMNlSw.JtZXAo9HhR9t-8Wl3gxJgnoM4--rtmDEUDbXSWezbFyU-CoB_nyfxbRQ4kdoN4-5aJ3Tgx4YHdikicqAhc_cezB2ZntjxkB4rEDx1A		Chord recognition																
 2017	unpublished	End-to-end musical key estimation using a convolutional neural network	Korzeniowski, Filip and Widmer, Gerhard	https://arxiv.org/pdf/1706.02921.pdf																		
 2017	inproceedings	MediaEval 2017 AcousticBrainz genre task: Multilayer perceptron approach	Koutini, Khaled and Imenina, Alina and Dorfer, Matthias and Gruber, Alexander Rudolf and Schedl, Markus	http://www.cp.jku.at/research/papers/Koutini_2017_mediaeval-acousticbrainz.pdf																		
-2017	unpublished	Classification-based singing melody extraction using deep convolutional neural networks	Kum, Sangeun and Nam, Juhan	https://www.preprints.org/manuscript/201711.0027/v1	No	F0	No	[LabROSA](http://labrosa.ee.columbia.edu/projects/melody/) & [MedleyDB](http://medleydb.weebly.com/) & [Jamendo](http://www.mathieuramona.com/wp/data/jamendo/) & [RWC](https://staff.aist.go.jp/m.goto/RWC-MDB/) & [iKala](http://mac.citi.sinica.edu.tw/ikala/) & [MIR-1K](https://sites.google.com/site/unvoicedsoundseparation/mir-1k) & [ADC2004](http://labrosa.ee.columbia.edu/projects/melody/)	Keras	CNN	0.3	No	100	Pitch shift -2, -1, +1, +2 semitones			Leakey ReLU		0.02	SGD	2	
+2017	unpublished	Classification-based singing melody extraction using deep convolutional neural networks	Kum, Sangeun and Nam, Juhan	https://www.preprints.org/manuscript/201711.0027/v1	No	F0	No	[LabROSA](http://labrosa.ee.columbia.edu/projects/melody/) & [MedleyDB](http://medleydb.weebly.com/) & [Jamendo](http://www.mathieuramona.com/wp/data/jamendo/) & [RWC](https://staff.aist.go.jp/m.goto/RWC-MDB/) & [iKala](http://mac.citi.sinica.edu.tw/ikala/) & [MIR-1K](https://sites.google.com/site/unvoicedsoundseparation/mir-1k) & [ADC2004](http://labrosa.ee.columbia.edu/projects/melody/)	Keras	CNN	0.3	No	100	Pitch shift -2, -1, +1, +2 semitones			Leaky ReLU		0.02	SGD	2	
 1989	article	The representation of pitch in a neural net model of chord classification	Laden, Bernice and Keefe, Douglas H.	http://www.jstor.org/stable/3679550		Chord recognition																
 2009	inproceedings	Unsupervised feature learning for audio classification using convolutional deep belief networks	Lee, Honglak and Pham, Peter and Largman, Yan and Ng, Andrew Y	http://papers.nips.cc/paper/3674-unsupervised-feature-learning-for-audio-classification-using-convolutional-deep-belief-networks.pdf		Speaker gender recognition		[TIMIT](https://catalog.ldc.upenn.edu/LDC93S1)		CDBN												
 2017	article	Multi-level and multi-scale feature aggregation using pre-trained convolutional neural networks for music auto-tagging	Lee, Jongpil and Nam, Juhan	https://arxiv.org/pdf/1703.01793v2.pdf																		

diff --git a/fig/articles_per_year.png b/fig/articles_per_year.png
diff --git a/fig/pie_chart_architecture.png b/fig/pie_chart_architecture.png
diff --git a/fig/pie_chart_dataset.png b/fig/pie_chart_dataset.png
diff --git a/fig/pie_chart_framework.png b/fig/pie_chart_framework.png
diff --git a/fig/pie_chart_task.png b/fig/pie_chart_task.png
diff --git a/frameworks.md b/frameworks.md
@@ -4,6 +4,7 @@ Please refer to the list of useful acronyms used in deep learning and music: [ac
 
 - Caffe
 - Keras
+- Keras-TensorFlow
 - Keras-Theano
 - Not disclosed
 - PyTorch

diff --git a/publication_type.md b/publication_type.md
@@ -52,5 +52,6 @@
 - SMC
 - WASPAA
 - WIMP
+- [IEEE_ICTAI](http://ictai2017.org/)
 - [NIPS](https://nips.cc/)
 - [NIPS_ML4Audio](https://nips.cc/Conferences/2017/Schedule?showEvent=8790)
-Original file line number
+Diff line change
@@ Expand Up @@
     - Caffe
     - Keras
+    - Keras-TensorFlow
     - Keras-Theano
     - Not disclosed
     - PyTorch
@@ Expand Down @@