update

content/dataset.md

@@ -7,8 +7,11 @@ weight: 80
 
 
 The training set can be downloaded here, using the password which will be provided to all registered teams: [ICASSP-2023-eeg-decoding-challenge-dataset](https://kuleuven-my.sharepoint.com/:f:/g/personal/lies_bollens_kuleuven_be/EkaIjOmoPIRHmYLdLK8b2VQBY_2ouqNSnHHTHyRl3Zn-2w?e=KhX7d0)
+
+For more details concerning the dataset, we refer to [the dataset paper](https://www.biorxiv.org/content/10.1101/2023.07.24.550310v1).
 
 
+
 # EEG
 
 Electroencephalography (EEG) is a non-invasive method to record electrical activity in the brain, which is generated by ionic currents that

content/homepage_sections/general_description.md

@@ -4,6 +4,10 @@ weight: 10
 description: "General description"
 ---
 
+## This Challenge is finished 
+This webpage describes the ICASSP Auditory EEG version of 2023. This challenge is now closed. Browse to The [new challenge page](https://exporl.github.io/auditory-eeg-challenge-2023/) 
+for the ICASSP Auditory EEG 2024 challenge. This page will not be updated or maintained any further. 
+
 ## Challenge Call 
 
 Various neuroimaging techniques can be used to investigate how the brain processes sound.

content/homepage_sections/leaderboard.md

@@ -6,11 +6,12 @@ description: "Get started"
 ## Get started
 
 1) Send a mail to [[email protected]]([email protected]) with the names of the team members, emails, and affiliations. You will receive a password to download the data  
-2) Download the data from [ICASSP-2023-eeg-decoding-challenge-dataset](https://kuleuven-my.sharepoint.com/:f:/g/personal/lies_bollens_kuleuven_be/EkaIjOmoPIRHmYLdLK8b2VQBY_2ouqNSnHHTHyRl3Zn-2w?e=KhX7d0)
+2) Download the data from [https://rdr.kuleuven.be/dataset.xhtml?persistentId=doi:10.48804/K3VSND](our official repository) or get the already zipped files from  [ICASSP-2023-eeg-decoding-challenge-dataset](https://kuleuven-my.sharepoint.com/:f:/g/personal/lies_bollens_kuleuven_be/EkaIjOmoPIRHmYLdLK8b2VQBY_2ouqNSnHHTHyRl3Zn-2w?e=KhX7d0)
    - **split_data(.zip)** contains already preprocessed, split and normalized data; ready for model training/evaluation. If you want to get started quickly, you can opt to only download this folder/zipfile.
    - **preprocessed_eeg(.zip)** and **preprocessed_stimuli(.zip)** contain preprocessed EEG and stimuli files ( speech envelope and mel spectrogram features) respectively. At this stage data is not yet split into different sets and not normalized. To go from this to the data in **split_data.zip**, you will have to run _task*/create_data/split_and_normalize.py_ for the task you want to work on.
    - **raw_eeg(_x.zip)** and **stimuli(.zip)** contain the raw EEG and stimuli files. If you want to process the stimuli files, you can run _task*/create_data/speech_features.py_. Speech Envelope and/or mel spectrogram features will be stored in the processed_stimuli. Currently, no preprocessing code is made available to preprocess EEG, so you will have to write your own implementation or use the precomputed processed_eeg folder.
 
+For more details concerning the dataset, we refer to [the dataset paper](https://www.biorxiv.org/content/10.1101/2023.07.24.550310v1). 
 
 3) Clone the starting code from our [github repository](https://github.com/exporl/auditory-eeg-challenge-2023-code) and get started. 
 The repository contains preprocessing code, as well as baseline models for each of the tasks. 

content/homepage_sections/timeline.md

@@ -4,15 +4,3 @@ weight: 60
 description: "Timeline"
 ---
 
-
-## Timeline (anywhere on earth)
-
-- November 21, 2022: Registration opens
-- November 21, 2022: Release of training set, code, baseline methods and documentation
-- January 6, 2023: Release of evaluation test set
-- February 6, 2023: Deadline for submitting results for both tasks
-- February 20, 2023: ICASSP 2023 grand challenge 2-page paper deadline (top 5 teams only)
-- March 7, 2023: ICASSP 2023 grand challenge 2-page paper acceptance notification
-- March 14, 2023: ICASSP 2023 grand challenge 2-page camera-ready deadline
-- June 4-8, 2023: ICASSP 2023 conference
-- August 9, 2023: IEEE open journal of signal processing grand challenge papers deadline

content/task1/description.md

@@ -51,7 +51,7 @@ held-out stimuli.
 For test set 2, some stimuli have already appeared in the training set, but the subjects are unseen.
 
 
-For these test sets, we will provide pairs of (EEG, stimulus 1, and stimulus 2), with a length of 3 seconds, each with a unique identifier
+For these test sets, we provide pairs of (EEG, stimulus 1, and stimulus 2), with a length of 3 seconds, each with a unique identifier
 and a subject identifier. As an output, participants should submit a json dictionary file to an online form on our website which contains the
 predicted label for all EEG segments. Each entry in the submitted dictionary should be of the form **(EEG ID) : (label)**. The label is 0 if stimulus 1 matches EEG and 1 if stimulus 2 matches EEG. In case of absent EEG ID entries, the sample will be assigned the wrong label. Labels should be either 0 or 1.
 

layouts/shortcodes/chart_1.html

@@ -1,5 +1,5 @@
 {{ $w := default "100" (.Get 0) }}
-{{ $h := default "300" (.Get 1) }}
+{{ $h := default "600" (.Get 1) }}
 {{ $r := ( .Inner | chomp) }}
 {{ $seed := "foo" }}
 {{ $id := delimit (shuffle (split (md5 $seed) "" )) "" }}
@@ -129,7 +129,7 @@ <h3>
 
     const boxplotData = {
       // define label tree
-      labels: groupNames,
+      labels: groupNames.slice(10),
       datasets: [{
         label: 'Test set 1: held-out stories',
         backgroundColor: 'rgba(255,0,0,0.5)',
@@ -138,7 +138,7 @@ <h3>
         outlierColor: 'rgba(255,0,0,0.5)',
         padding: 10,
         itemRadius: 0,
-        data: withinResults
+        data: withinResults.slice(10)
       }, {
         label: 'Test set 2: held-out subjects',
         backgroundColor:  'rgba(0,0,255,0.5)',
@@ -147,7 +147,7 @@ <h3>
         outlierColor: 'rgba(0,0,255,0.5)',
         padding: 10,
         itemRadius: 0,
-        data:heldoutResults
+        data:heldoutResults.slice(10)
       }]
     };
     var  ctx = document.getElementById("canvas").getContext("2d");

layouts/shortcodes/chart_2.html

@@ -1,5 +1,5 @@
 {{ $w := default "100" (.Get 0) }}
-{{ $h := default "300" (.Get 1) }}
+{{ $h := default "600" (.Get 1) }}
 {{ $r := ( .Inner | chomp) }}
 {{ $seed := "foo" }}
 {{ $id := delimit (shuffle (split (md5 $seed) "" )) "" }}
@@ -127,7 +127,7 @@ <h3>
 
     const boxplotData = {
       // define label tree
-      labels: groupNames,
+      labels: groupNames.slice(4),
       datasets: [{
         label: 'Test set 1: held-out stories',
         backgroundColor: 'rgba(255,0,0,0.5)',
@@ -136,7 +136,7 @@ <h3>
         outlierColor: 'rgba(255,0,0,0.5)',
         padding: 10,
         itemRadius: 0,
-        data: withinResults
+        data: withinResults.slice(4)
       }, {
         label: 'Test set 2: held-out subjects',
         backgroundColor:  'rgba(0,0,255,0.5)',
@@ -145,7 +145,7 @@ <h3>
         outlierColor: 'rgba(0,0,255,0.5)',
         padding: 10,
         itemRadius: 0,
-        data:heldoutResults
+        data:heldoutResults.slice(4)
       }]
     };
     var  ctx = document.getElementById("canvas").getContext("2d");