Sorry, you need to enable JavaScript to visit this website.

THE MULTIMODAL INFORMATION BASED SPEECH PROCESSING (MISP) 2023 CHALLENGE: AUDIO-VISUAL TARGET SPEAKER EXTRACTION

DOI:
10.60864/ecyd-g369
Citation Author(s):
Shilong Wu, Chenxi Wang, Hang Chen, Yusheng Dai, Chenyue Zhang, Ruoyu Wang, Hongbo Lan, Jun Du, Chin-hui Lee, Jingdong Chen, Sabato Marco Siniscalchi, Odette Scharenborg, Zhong-Qiu Wang, Jia Pan, Jianqing Gao
Submitted by:
Shilong Wu
Last updated:
6 June 2024 - 10:27am
Document Type:
Presentation Slides
Event:
Presenters:
Hang Chen
Paper Code:
MMSP-L2.1
 

Previous Multimodal Information based Speech Processing (MISP) challenges mainly focused on audio-visual speech recognition (AVSR) with commendable success. However, the most advanced back-end recognition systems often hit performance limits due to the complex acoustic environments. This has prompted a shift in focus towards the Audio-Visual Target Speaker Extraction (AVTSE) task for the MISP 2023 challenge in ICASSP 2024 Signal Processing Grand Challenges. Unlike existing audio-visual speech enhancement challenges primarily focused on simulation data, the MISP 2023 challenge uniquely explores how front-end speech processing, combined with visual clues, impacts back-end tasks in real-world scenarios. This pioneering effort aims to set the first benchmark for the AVTSE task, offering fresh insights into enhancing the accuracy of back-end speech recognition systems through AVTSE in challenging and real acoustic environments. This paper delivers a thorough overview of the task setting, dataset, and baseline system of the MISP 2023 challenge. It also includes an in-depth analysis of the challenges participants may encounter. The experimental results highlight the demanding nature of this task, and we look forward to the innovative solutions participants will bring forward.

up
1 user has voted: Shilong Wu