Short-duration Speaker Verification (SdSV) Challenge 2020

Evaluate New Technologies in Short Duration Senarios

Welcome to SdSV Challenge 2020!

The main goal of the SdSV Challenge 2020 is to evaluate new technologies for text-dependent (TD) and text-independent (TI) speaker verification (SV) in short duration scenario.

The challenge evaluates SdSV with varying degree of phonetic overlap between the enrollment and test utterances. It is the first challenge with a broad focus on systematic benchmark and analysis on varying degree of phonetic variability on short-duration speaker recognition.

The evaluation dataset used for the challenge is drawn from the recently released multi-purpose DeepMine dataset[1]. The dataset has three parts and among them Part 1 is used for TD-SV while Part 3 is for TI-SV.

[1] H. Zeinali, L. Burget, J. Cernocky, A multi purpose and large scale speech corpus in Persian and English for speaker and speech recognition: the DeepMine database, in: Proc. ASRU 2019 The 2019 IEEE Automatic Speech Recognition and Understanding Workshop, 2019 (2019).

The Kaldi baseline recipe for both tasks can be found in this link. For running the baseline you should first download both VoxCeleb1 and VoxCeleb2 datasets. Then after downloading the challenge data, by putting the baseline code in the Kaldi egs directory you can run this code.

The full challenge evaluation plane version 1.1 can be found in this link. If you have any more questions regarding the challenge you can contact organizers via sdsvc2020[at]gmail.com.

Schedule[modified]

January 10, 2020 Release of evaluation plan
January 15, 2020 Evaluation platform open
January 10, 2020 Release of train, development and evaluation sets
April 17, 2020 Challenge deadline
April 27, 2020 Release of results
October 25, 2020 Post-challenge evaluation
May 8, 2020 Interspeech submission deadline
October 25-29, 2020 SdSV Challenge 2020 special session at Interspeech
 

Prizes

There will be three cash prizes for each task. The winners will be selected based on the results of the primary systems on the evaluation subset. In addition to the cash prize, each winner will receive a certificate for their achievement. The cash prizes are as follow:

Sponsors

Sharif DeepMine Ltd.
Computer Research Institute of Montreal (CRIM)
Phonexia Ltd.