CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Chen, Liu, Zehua, Li, Xiaolou, Li, Lantian, Wang, Dong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914834956681216
author Chen, Chen
Liu, Zehua
Li, Xiaolou
Li, Lantian
Wang, Dong
author_facet Chen, Chen
Liu, Zehua
Li, Xiaolou
Li, Lantian
Wang, Dong
contents The first Chinese Continuous Visual Speech Recognition Challenge aimed to probe the performance of Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR) on two tasks: (1) Single-speaker VSR for a particular speaker and (2) Multi-speaker VSR for a set of registered speakers. The challenge yielded highly successful results, with the best submission significantly outperforming the baseline, particularly in the single-speaker task. This paper comprehensively reviews the challenge, encompassing the data profile, task specifications, and baseline system construction. It also summarises the representative techniques employed by the submitted systems, highlighting the most effective approaches. Additional information and resources about this challenge can be accessed through the official website at http://cnceleb.org/competition.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10313
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge
Chen, Chen
Liu, Zehua
Li, Xiaolou
Li, Lantian
Wang, Dong
Computation and Language
Computer Vision and Pattern Recognition
The first Chinese Continuous Visual Speech Recognition Challenge aimed to probe the performance of Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR) on two tasks: (1) Single-speaker VSR for a particular speaker and (2) Multi-speaker VSR for a set of registered speakers. The challenge yielded highly successful results, with the best submission significantly outperforming the baseline, particularly in the single-speaker task. This paper comprehensively reviews the challenge, encompassing the data profile, task specifications, and baseline system construction. It also summarises the representative techniques employed by the submitted systems, highlighting the most effective approaches. Additional information and resources about this challenge can be accessed through the official website at http://cnceleb.org/competition.
title CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.10313