Merge branch 'master' of github.com:source-separation/tutorial

Author: justinsalamon

book/approaches/deep/introduction.md

@@ -6,7 +6,7 @@ We've now gotten some understanding of the general mechanics of source separatio
 now let's turn to Neural Network methods. Neural Network-based methods are
 commonly referred to as deep learning or deep net methods.
 
-```{image} ../images/data/source_separation_training.png
+```{image} ../../images/data/source_separation_training.png
 :align: center
 ```
 

book/conclusions/concluding_remarks.md

@@ -2,9 +2,14 @@ Concluding Remarks
 ==================
 
 
-In this tutorial we have learned all about source separation. We started with
-an overview of the basics before learning about modern techniques. We then
-dove into data, and concluded with how to train your own models. We hope this
-tutorial has been useful for you.
+In this tutorial we have taken a pragmatic approach to learning
+about source separation. From the basics, through data and training,
+we have explored open source projects that enables modern source
+separation research and can further your own projects. We hope
+this tutorial has been as fun to read as it was for us to put it
+together.
 
-Thanks so much!
+
+Thank you so much for reading! Happy separating! :D
+
+- Ethan, Prem, and Justin

book/first_steps/byo_hpss.ipynb

@@ -269,7 +269,7 @@
     "# Comment out the line above to run this cell\n",
     "# interactively in Colab or Jupyter Notebook\n",
     "\n",
-    "my_hpss.interact()"
+    "my_hpss.interact(share=True, source='microphone')"
    ]
   },
   {

book/intro/open_src_projects.md

@@ -106,7 +106,8 @@ fixes some of the issues that `mir_eval` has. Some recent developments like
 It has become increasingly common for researchers to release code accompanying
 their research papers. In the era of deep learning, the trained models are also
 sometimes released. Here is a non-exhaustive list of some recent open source
-projects.
+projects. We have prioritized open source projects with code and downloadable
+trained models by the original authors of the research papers described.
 
 We will discuss some of these architectures in more detail in later sections,
 but here we will provide some highlights and links to their Github repositories,
@@ -235,15 +236,15 @@ There are so many wonderful open source projects out there, and we would love to
 do a deep dive into all of them. But there's only so much time, so we choose
 `nussl` and `Scaper` for a few reasons:
 
-- **We believe that the combination of `nussl`+`Scaper` provides a solid foundation
-  for all source separation projects.** We hope to convince you of the 
-  utility of both of these projects as you work through this tutorial.
+- **The combination of `nussl`+`Scaper` provides a solid foundation
+  for all source separation projects.** These projects provide solutions for
+  networks, data, evaluation, and interaction all in one.
 
 - **The lessons we will explore in these two projects extend beyond them.**
   There are many common themes and design patterns in this area of research,
   and as we progress you will start to see the themes again and again. We
   believe that `nussl`+`Scaper` is a good way to explore these themes so that
-  you can understand _any_ modern source separation system.
+  you can understand the structure of modern source separation systems.
 
 - **We are the primary developers for these projects.** We _really_ understand
   these tools because, well, we built them! That means we are well equipped to

book/intro/src_sep_101.md

@@ -147,17 +147,10 @@ speaker products like Amazon's Alexa, but it has musical applications in
 [iZotopes Spire](https://www.izotope.com/en/products/spire-studio.html).
 
 
-## A Historical Perspective
+## Next Steps...
 
-Source Separation is a problem that has been studied for decades. Although we won't
-be able to cover everything in detail, this tutorial will provide a brief overview
-of methods that we think provide a representative demonstration of important concepts and
-provide practical value.
-
-In general, modern source separation approaches fall into two broad categories: blind
-source separation approaches and data-driven approaches. Blind source separation
-approaches are algorithms that make explicit assumptions about the auditory scene
-upon which they operate
+In the next section we will provide a brief overview of the open source landscape
+before diving into the basics of source separation.
 
 
 [^fn1]: Some creative applications might not have such strict demands; when using

book/landing.md

@@ -1,17 +1,17 @@
-Welcome!
-========
+Open-Source Tools & Data for Music Source Separation
+====================================================
+
+**By Ethan Manilow, Prem Seetharaman, and Justin Salamon**
+
+Shared under [Creative Commons BY-NC-SA 4.0](https://github.com/source-separation/tutorial/blob/master/LICENSE.txt).
 
 ```{image} images/data/source_separation_io.png
 ---
 alt: Separating of musical signals.
 ```
 
 Hello and welcome to the website for our tutorial at [ISMIR 2020](https://ismir.github.io/ISMIR2020/)!
-We're excited that you've decided to join us! Our tutorial is entitled...
-
-### Open-Source Tools & Data for Music Source Separation: A Pragmatic Guide for the MIR Practitioner
-
-**By Ethan Manilow, Prem Seetharaman, and Justin Salamon**
+We're excited that you've decided to join us!
 
 In this tutorial, we will guide you through modern, open-source tooling and datasets
 for running, evaluating, researching, and deploying source separation approaches. 

book/references.bib

@@ -759,10 +759,10 @@ @misc{musdb18-hq
 
 @inproceedings {nussl
     author = {Ethan Manilow and Prem Seetharaman and Bryan Pardo},
-    title = "The Northwestern University Source Separation Library",
-    publisher = "Proceedings of the 19th International Society of Music Information Retrieval
-        Conference ({ISMIR} 2018), Paris, France, September 23-27",
-    year = 2018
+    title = {"The Northwestern University Source Separation Library"},
+    booktitle = {"Proceedings of the 19th International Society of Music Information Retrieval
+        Conference ({ISMIR} 2018), Paris, France, September 23-27"},
+    year = {2018}
 }