The Deep End Music Extended Essay

The extended essay is a required component of the IB Diploma Programme, it is an independent, self-directed piece of research, finishing with a 4,000-word paper. The following 6 tips are to help you get started on writing a quality extended essay.

Tip 1: Get started !

You will have conduct a substantial amount of research before you can even start writing your extended essay so the sooner you get started the better. Make sure that you are clear on the deadlines, each school is different and may set their deadlines differently. If you are prone to procrastination have a look at this very entertaining TED talk by Tim Urban entitled “Inside the mind of a master procrastinator”.

Tip 2: Enjoy your subject !

Pick a subject to write about that not only interests you but one that you are passionate about ! Think of all your subjects, narrow the list down to your favourites and then pick your topics from the chapters that interest you the most. Writing that is passionate and authentic is always more engaging.

Tip 3: Dig deep !

Most students only use the usual sources for their research in the form of books, articles, video etc. However, if you really want to get into your subject you should also have a look through the academic papers written by professors who specialise in these subjects. Have a look through google scholar for papers written on your subject and quote from these in your essay for some extra depth and rigour on your topic.

Tip 4:The word count is not the enemy !

Many students waste a lot of time and energy worrying about the word count. The good news is that most students end up having to reduce their text to 4000 words at the end. If you have done your research and analysis properly the word count will take care of itself. Remember the point of the essay is not to write 4000 words but to examine a topic and present your analysis.

Tip 5: Topic too broad

Often students choose topics that are too broad in scope and require far too much research. An example of a topic that is too broad might be “World War 1”, this would undoubtedly fill many volumes rather than just a essay. If you are finding this difficult try comparison type essay topics which are clear on what is being compared and to what depth.

Tip 6: Go beyond description

Your IB extended essay should be analytical not just descriptive. You must convincingly answer the research question and argue for your thesis, presenting evidence to support your arguments. You must evaluate your sources and demonstrate an ability to think and write critically and analytically. The analysis and evaluation of your topic is what counts.

Have you got any other tips that might help fellow IB students? Let us know in the comments section below.

What is TOK and CAS in the IB Diploma Programme? 


Convolutional Neural Networks (CNN) have been applied to diverse machine learning tasks for different modalities of raw data in an end-to-end fashion. In the audio domain, a raw waveform-based approach has been explored to directly learn hierarchical characteristics of audio. However, the majority of previous studies have limited their model capacity by taking a frame-level structure similar to short-time Fourier transforms. We previously proposed a CNN architecture which learns representations using sample-level filters beyond typical frame-level input representations. The architecture showed comparable performance to the spectrogram-based CNN model in music auto-tagging. In this paper, we extend the previous work in three ways. First, considering the sample-level model requires much longer training time, we progressively downsample the input signals and examine how it affects the performance. Second, we extend the model using multi-level and multi-scale feature aggregation technique and subsequently conduct transfer learning for several music classification tasks. Finally, we visualize filters learned by the sample-level CNN in each layer to identify hierarchically learned features and show that they are sensitive to log-scaled frequency. View Full-Text

Keywords: convolutional neural networks; music classification; raw waveforms; sample-level filters; downsampling; filter visualization; transfer learningconvolutional neural networks; music classification; raw waveforms; sample-level filters; downsampling; filter visualization; transfer learning

►▼ Figures

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

Share & Cite This Article

MDPI and ACS Style

Lee, J.; Park, J.; Kim, K.L.; Nam, J. SampleCNN: End-to-End Deep Convolutional Neural Networks Using Very Small Filters for Music Classification. Appl. Sci.2018, 8, 150.

AMA Style

Lee J, Park J, Kim KL, Nam J. SampleCNN: End-to-End Deep Convolutional Neural Networks Using Very Small Filters for Music Classification. Applied Sciences. 2018; 8(1):150.

Chicago/Turabian Style


Leave a Reply

Your email address will not be published. Required fields are marked *