/ismir-2019-posters

ismir-2019-posters

How to add your poster

Add it by making a pull request!

  • fork this repo and clone it to your local computer
  • update the repo with your poster and its description
    • git add your poster image to posters/ folder
      • or just directly upload to the folder on your webbrowser
    • update your repo's readme.md with the right format (you can also directly edit it on webbrowser) 
      ### [poster session code] TITLE | LINK_TO_PAPER | LINK_TO_CODE | LINK_TO_WHATEVER

AUTHOR NAMES

> "SHORT DESCRIPTION THAT YOU USED IN THE CONFERENCE WEBSITE"

POSTER IMAGE HERE WITH A RELATIVE LINK, i.e.,
![POSTER SESSION CODE](posters/POSTER_SESSION_CODE-YOUR_POSTER_FILE_NAME.png)
  • commit, push
  • make sure it looks good on readme.md of your forked repo
  • make a pull request
  • DO NOT CHANGE OTHERS' POSTERS - WE DON'T NEED A MERGE CONFLICT HERE!

Sessions

Session A, Session B, Session C, Session D, Session E, Session F, Session G, Late-Breaking/Demo MIREX

Session A

Session B

[B-02] Deep Unsupervised Drum Transcription | paper | code

Keunwoo Choi; Kyunghyun Cho

"DrummerNet is a drum transcriber trained in an unsupervised fashion. DrummerNet learns to transcribe by learning to reconstruct the audio with the transcription estimate. Unsupervised learning + a large dataset allow DrummerNet to be less-biased."

B-02 Poster

Session C

Session D

Session E

Session F

Session G

Late-Breaking/Demo

[L-07] Improving Music Tagging from Audio with User-Track Interactions | paper

Andres Ferraro; Jae Ho Jeon; Jisang Yoon; Xavier Serra; Dmitry Bogdanov

"We propose to improve the tagging of music by using audio and collaborative filtering information (user-track interactions). We use Matrix Factorization (MF) to obtain a representation of the tracks from the user-track interactions and map those representations to the tags predicted from audio. The preliminary results show that following this approach we can increase the tagging performance."

L-07 Poster

[L-10] Creating a Tool for Faciltiating and Researching Human Annotation of Musical Patterns | paper | code

Stephan Wells; Iris Yuping Ren; Anja Volk

"Musical patterns (repeated segments of music) are highly widespread in all varieties of music, and annotations of such patterns are valuable in many areas of music information retrieval. Unfortunately, there is a lack of expert annotations of musical patterns, and most annotation is done by hand. In this project, we introduce a novel software, ANOMIC, designed for users to intuitively annotate repeated musical segments, and we perform a user study which yields a large database of annotations done using the tool. We find that the tool’s reception was strongly positive and show that the annotations done with it reach high levels of inter-annotator agreement compared to traditional approaches."

L-10 Poster

MIREX