Loading
2 Follower
17 Following
alina_porechina

Location

UZ

Badges

0
0
0

Activity

Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Mon
Wed
Fri

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

Latest submissions

See All
failed 219841
failed 219840
graded 219656

Music source separation of an audio signal into separate tracks for vocals, bass, drums, and other

Latest submissions

See All
failed 219841
failed 219840
graded 219656

Source separation of a cinematic audio track into dialogue, sound-effects and misc.

Latest submissions

No submissions made in this challenge.
Participant Rating
kimberley_jensen 0
subatomicseer 0
Participant Rating
kim_min_seok 0
junicus 0
MalcolmX 0
clement_tabary 0
yoyololicon 0
subatomicseer 0
tushar_dhyani 0
Tomasyu 0
Bonum 114
greentim 0
holaamy 0
jules.wang 0
richard2357 0
sandesh_bharadwaj97 0
kimberley_jensen 0
ZFTurbo 0
dipam
alina_porechina has not joined any teams yet...

Sound Demixing Challenge 2023

Secrets of success (MDX, leaderboard B)

Over 1 year ago

Hello everyone. I’m currently in 4th place on the leaderboard B. I’m using demucs baseline and another model trained from scratch for vocals. It would be funny if someone told me how to improve my result by 0.24 to get into the prizes :slight_smile:

Reasons of submission failure

Over 1 year ago

(post deleted by author)

Secrets of success (MDX, leaderboard C)

Over 1 year ago

@JackZ @JusperLee @ouYi @XavierJ @MalcolmX
If someone will share how to get >9.900 on vocals, then I will share how to get this result:
9.851 bass
9.210 drums
6.603 other
9.168 vocals

Veni, vidi, vici

Over 1 year ago

It looks a little strange that at the end of the challenge a participant from Korea University β€œjunicus” gets 3rd and 2nd place on the A and B leaderboards on the first attempt. Another leader, the β€œkuielab” team is also from Korea University. I hope that AIcrowd Team will carefully check the code of these participants for borrowing (private sharing) after the challenge ends.

Slow downloading of musdb18hq

Over 1 year ago

My training pipeline for leaderboard A and B starts with downloading of dataset from https://sdx-2023-data-bucket.s3.amazonaws.com. Dear organizers, could you upload full version of musdb18hq to this cloud? Download speed from zenodo is about 400 KB/s.

Feedback and suggestion

Over 1 year ago

@mohanty
It would be more convenient if the submission counter resets at 00:00 UTC

Reasons of submission failure

Over 1 year ago

@dipam
Also please rerun #214696 and #214694 (β€œEvaluation timed out”)

Reasons of submission failure

Over 1 year ago

@dipam

#214686
#214701
Can you please rerun these submissions?
(β€œScoring failed. Please contact the admins”)

Today, due to my mistake, 4 submissions failed with β€œPrediction too slow”. They ran simultaneously. Could this have somehow overloaded the system and caused scoring to fail?

Secrets of success (MDX, leaderboard C)

Over 1 year ago

I guess they are using β€œband-split RNN”

Secrets of success (MDX, leaderboard C)

Over 1 year ago

Can anyone share any ideas on how the top 3 teams on the β€œC” leaderboard got such high SDR on β€œvocals” and β€œother”?

Post deleted by author

Almost 2 years ago

(topic deleted by author)

Reasons of submission failure

Almost 2 years ago

@dipam

Today 3/5 of my submissions failed unexpectedly

Reasons of submission failure

Almost 2 years ago

#210459
Demixing got stuck (2/2 - 0.689x, 6/27 - 0.692x), then I got β€œEvaluation timed out”

Reasons of submission failure

Almost 2 years ago

#210461
After successful demixing (2/2 - 1.73x, 27/27 - 1.749x) I got the message: β€œEvaluation timed out”

Reasons of submission failure

Almost 2 years ago

#210438
After demixing I got the message: β€œScoring failed. Please contact the admins.”

What baselines are coming up?

Almost 2 years ago

Thanks. Can you please post the entire presentation from town hall?

What baselines are coming up?

Almost 2 years ago

What baselines for MDX (A,B,C) and CDX (A,B) will be published during the challenge?

Feedback and suggestion

Almost 2 years ago

(post deleted by author)

Reasons of submission failure

Almost 2 years ago

@dipam

Today I successfully resubmitted code from failed #210197 (2/2 - 0.771x, 3/27 - 0.769x) as #210246 (2/2 - 0.757x, 27/27 - 0.749x)

Reasons of submission failure

Almost 2 years ago

@dipam

My understanding is that the speed of my model is constant.

#210197 (2/2 - 0.771x, 3/27 - 0.769x) may have fallen due to low speed.

It is less likely that #210059 fell due to low speed (2/2 - 0.926x, 9/27 - 0.913x).

#210078 and #210117 are identical. #210078 returned β€œEvaluation timed out” during validation phase. #210117 was evaluated quickly and successfully (2/2 - 3.369x, 27/27 - 3.479x).

I think it’s better to turn on the second counter instead of looking for the causes of rare crashes.

alina_porechina has not provided any information yet.