CN-Celeb

Welcome to the CNSRC Workshop 2022. The workshop is a forum to exchange ideas regarding state-of-the-art speaker recognition techniques under more challenging conditions. The workshop is held as a special event at Odyssey 2022.

The CNSRC 2022 participants are required to attend the workshop. The workshop will include CNSRC introduction, technical overview, winner announcement and system description sharing.

News

2022-June-17 Invitation from Odyssey-CNSRC Workshop 2022.

2022-June-27The Newsletter of Odyssey-CNSRC Workshop 2022.

Schedule

The CNSRC Workshop 2022 takes place on 27th June 2022 at 20:00-22:00 Beijing Time (UTC+8).

Considering the global COVID-19 pandemic, the CNSRC Workshop 2022 is held entirely online.

Video Playback: Scan via WeChat

SpeechHome

Programme

Time: 27th June 2022, 20:00-22:00 Beijing Time (UTC+8)

20:00 - CNSRC 2022 Introduction. Dong Wang, THU. [slides]

20:10 - Technical overview. Lantian Li, THU. [slides]

20:30 - Winner announcement. Qingyang Hong (XMU) and Hui Bu (AISHELL). [slides]

20:40 - Participant talks.

T082 Zhengyang Chen, Shanghai Jiaotong University. [slides]

T022 Minqiang Xu, SpeakIn. [slides]

T106 Shiwei Jiang, Shanxi University. [slides]

T070 Xinmei Su, Beijing Institute of Technology. [slides]

T125 Zhe Li, The HongKong Polytechnic University. [slides]

21:45 - Discussion.

Special Session: CNSRC 2022 at Odyssey 2022

Time: 1st July 2022, 21:05 ~ 21:20, Beijing Time (UTC+8)

Introduction by the Organizers. Qingyang Hong, XMU. [slides]

Ranking list

Through rigorous screening, including data usage confirmation, system description and extra validation test, the organising committee has confirmed the final ranking list on each task and each track. The CNSRC 2022 final ranking list can be seen from [Here].

Task 1 SV Fixed Track Ranking List Based on CN-Celeb.Eval with minDCF

Rank	TeamID	CN-Celeb.Eval		CN-Celeb.Valid		Report
Rank	TeamID	minDCF(0.01)	EER(%)	minDCF(0.01)	EER(%)	Report
1	T082	0.2975	4.911	0.4041	5.812	pdf
2	T022	0.3185	5.953	0.4106	5.796	pdf
3	T106	0.3399	5.728	0.5266	6.967	pdf
4	T057	0.3445	7.344	0.6062	8.326	pdf
5	T095	0.3603	6.826	0.4811	5.832	pdf
6	T113	0.3999	7.564	0.5246	7.759	pdf
7	T053	0.4159	7.333	0.6737	9.002	pdf
8	T009	0.4195	8.871	0.5402	9.006	pdf
9	T028	0.4248	9.006	0.6856	11.062	pdf
10	T126	0.4263	7.592	0.6147	8.833	pdf
11	T067	0.4279	8.758	0.6039	9.171	pdf
12	T042	0.4504	8.223	0.5567	7.280	pdf

Task 1 SV Open Track Ranking List Based on CN-Celeb.Eval with minDCF

Rank	TeamID	CN-Celeb.Eval		CN-Celeb.Valid		Report
Rank	TeamID	minDCF(0.01)	EER(%)	minDCF(0.01)	EER(%)	Report
1	T022	0.2394	4.663	0.2482	4.738	pdf
2	T082	0.2975	4.911	0.4041	5.812	pdf
3	T102	0.3121	5.114	0.3459	5.422	pdf
4	T106	0.3399	5.728	0.5266	6.967	pdf
5	T057	0.3445	7.344	0.6062	8.326	pdf
6	T009	0.3707	7.384	0.4096	6.999	pdf
7	T126	0.4125	6.770	0.5939	7.936	pdf
8	T021	0.4339	6.792	0.6977	10.317	pdf

Task 2 SR Open Track Ranking List Based on SR.eval with mAP

Rank	TeamID	SR.eval (mAP)	Report
1	T070	0.7085	pdf
2	T102	0.7071	pdf
3	T022	0.6106	pdf
4	T082	0.4626	pdf
5	T126	0.3563	pdf
6	T057	0.3004	pdf

Organization Committees

Dong Wang, Tsinghua University, Beijing, China
Qingyang Hong, Xiamen University, Xiamen, China
Lantian Li, Tsinghua University, Beijing, China
Wenqiang Du, Tsinghua University, Beijing, China
Yang Zhang, Tsinghua University, Shenzhen, China
Tao Jiang, TalentedSoft, Xiamen, China
Hui Bu, AISHELL, Beijing, China
Xin Xu, AISHELL, Beijing, China

Please contact e-mail cnsrc@cslt.org if you have any queries.

Acknowledgements

This work is supported by the National Natural Science Foundation of China (NSFC) under Grants No.61633013 and No.62171250.

Welcome to the CNVSRC Workshop 2023. The workshop is a forum to exchange ideas regarding Chinese large vocabulary visual speech recognition techniques. The workshop is held as a special event at NCMMSC 2023.

The workshop includes CNVSRC introduction, rank announcement, technical overview and system description sharing.

Schedule

The CNVSRC Workshop 2023 takes place on 9th December 2023 at 18:30-19:50 Beijing Time (UTC+8).

The workshop is conducted in a combination of online and offline mode.

Video Playback: Scan via Tencent meeting

Programme

Time: 9th December 2023 at 18:30-19:50 Beijing Time (UTC+8)

18:30 – CNVSRC 2023 Introduction. Dong Wang, THU. [slides]

18:42 – Opening Speech. Ke Li, DataOcean AI.

18:45 – Rank Announcement. Hui Bu (Speech Home) and Ke Li (DataOcean AI). [slides]

18:55 – Technical overview. Chen Chen, THU. [slides]

19:05 – Participant talks
T266 GUA Speech [slides]

T238 VII-BUPT [slides]

T237 NPU-ASLP-LiAuto [slides]

T267 RoyalFlush [slides]

19:45 – Discussion

Ranking list

Through rigorous screening, including data usage confirmation and system description, the organising committee has confirmed the final ranking list on each task and each track. The CNVSRC 2023 final ranking list is as follows:

Task 1 Single-speaker VSR Fixed Track

Rank	TeamID	CER on CNVSRC.Single.Eval	Report
1	T237	34.7601%	Report-t237.pdf
2	T266	38.0856%	Report-t266.pdf
3	T290	39.4707%	Report-t290.pdf
4	T238	40.5160%	Report-t238.pdf
5	T267	41.6213%	Report-t267.pdf

Task 1 Single-speaker VSR Open Track

Rank	TeamID	CER on CNVSRC.Single.Eval	Report
1	T237	34.7601%	Report-t237.pdf

Task 2 Multi-speaker VSR Fixed Track

Rank	TeamID	CER on CNVSRC.Multi.Eval	Report
1	T244	53.6815%	Report-t244.pdf
2	T267	54.5587%	Report-t267.pdf

Task 2 Multi-speaker VSR Open Track

Rank	TeamID	CER on CNVSRC.Multi.Eval	Report
1	T237	41.0550%	Report-t237.pdf
2	T244	53.6815%	Report-t244.pdf

Organization Committees

DONG WANG, Center for Speech and Language Technologies, Tsinghua University, China
CHEN CHEN, Center for Speech and Language Technologies, Tsinghua University, China 
LANTIAN LI, Beijing University of Posts and Telecommunications, China
KE LI, Beijing Haitian Ruisheng Science Technology Ltd., China
HUI BU, Beijing AISHELL Technology Co. Ltd, China

Please contact e-mail cnvsrc@cnceleb.org if you have any queries.

Welcome to the CNVSRC Workshop 2024. The workshop is a forum to exchange ideas regarding Chinese large vocabulary visual speech recognition techniques. The workshop is held as a special event at NCMMSC 2024.

The workshop includes CNVSRC 2024 introduction, opening speech, rank announcement, technical report and system description sharing.

Schedule

2024/05/08 Registration kick-off

2024/05/08 Data release

2024/05/08 Baseline system release

2024/07/01 Submission system open

2024/08/01 Deadline for result submission

2024/08/16 Workshop at NCMMSC 2024

The CNVSRC Workshop 2024 takes place on 16th August 2024 from 10:00 to 11:30 Beijing Time (UTC+8). The workshop is conducted in both online and offline modes.

Video Playback: Scan via WeChat

Programme

Time: 16th August 2024 at 10:00-11:30 Beijing Time (UTC+8)

10:00 CNVSRC 2024 Introduction. - Dong Wang, THU. [slides]

CNVSRC 2024 Introduction

10:20 CNVSRC 2024 Opening Speech. - Xiaoman Wang, DataOcean AI.

CNVSRC 2024 Opening Speech

10:25 CNVSRC 2024 Opening Speech. - Hui Bu, Speech Home.

CNVSRC 2024 Opening Speech

10:30 CNVSRC 2024 Rank Announcement. - Xiaoman Wang (DataOcean AI), Hui Bu (Speech Home). [slides]

CNVSRC 2024 Rank Announcement

10:40 CNVSRC 2024 Technical Report. - Zehua Liu, BUPT. [slides]

CNVSRC 2024 Technical Report

10:55 CNVSRC 2024 Participant Talks. - He Wang, T237-FlySpeech-NPU. [slides]

CNVSRC 2024 Participant Talks

CNVSRC 2024 Participant Talks. - Meng Miao, T244-Dream Boy-IMU. [slides]

CNVSRC 2024 Participant Talks

CNVSRC 2024 Participant Talks. - Fei Su, T405-Sophin-WHU, DKU. [slides]

CNVSRC 2024 Participant Talks

11:30 CNVSRC 2024 Photo

CNVSRC 2024 Photo

Ranking List

After rigorous screening, including confirmation of data usage and system descriptions, the organizing committee has confirmed the final rankings for each task and track. The CNVSRC 2024 final ranking list is as follows:

Task 1 Single-speaker VSR Fixed Track

Rank	TeamID	CER on CNVSRC.Single.Eval	Report
1	T237	30.4679%	Report-T237.pdf
2	T244	39.3110%	Report-T244.pdf

Task 1 Single-speaker VSR Open Track

Rank	TeamID	CER on CNVSRC.Single.Eval	Report
1	T170	30.0680%	匿名提交
2	T237	30.4679%	Report-T237.pdf

Task 2 Multi-speaker VSR Fixed Track

Rank	TeamID	CER on CNVSRC.Multi.Eval	Report
1	T237	34.2955%	Report-T237.pdf
2	T170	45.3244%	匿名提交
3	T244	47.9259%	Report-T244.pdf

Task 2 Multi-speaker VSR Open Track

Rank	TeamID	CER on CNVSRC.Multi.Eval	Report
1	T237	34.2955%	Report-T237.pdf
2	T170	38.3454%	匿名提交
3	T405	57.7762%	Report-T405.pdf

Organization Committees

DONG WANG, Center for Speech and Language Technologies, Tsinghua University, China
ZEHUA LIU, Beijing University of Posts and Telecommunications, China
LANTIAN LI, Beijing University of Posts and Telecommunications, China
XIAOMAN WANG, Beijing Haitian Ruisheng Science Technology Ltd., China
HUI BU, Beijing AISHELL Technology Co. Ltd, China

Please contact e-mail cnvsrc@cnceleb.org if you have any queries.