In this work, we firstly publish CN-Celeb, a large-scale Not only limited in size but are also recorded under controlled conditions, which cannot support conclusive research on the multi-genre problem.
Unfortunately, the few existing multi-genre corpora are This mismatch leads to complex andĬomposite inter-session variations, both intrinsic (i.e., speaking style, physiological status) and extrinsic (i.e., recording device, background noise). Research on speaker recognition is extending to address the vulnerability in the wild conditions,Īmong which genre mismatch is perhaps the most challenging, for instance, enrollment with reading speech while testing with conversational or singing audio. Our database is free for researchers and can be downloaded This resultĭemonstrates that in real-life conditions, the performance ofĮxisting techniques might be much worse than it was thought. Experiments conducted with two state-of-the-art speaker recognition approaches (i-vector and x-vector) show that the performance on CN-Celeb is far inferior to the one obtained on VoxCeleb, a widely used speaker recognition dataset. This datasetĬontains more than 130, 000 utterances from 1, 000 ChineseĬelebrities, and covers 11 different genres in real world. In this paper, we present CN-Celeb, a large-scale speaker recognition dataset collected ‘in the wild’. Research on speaker recognition in unconstrained conditions. Over-optimistic performance and do not meet the request of However, most publicly available datasets are collected under constrained environments, i.e., with little noiseĪnd limited channel variation. The variations on ambient, channel and emotion could be arbitrary. Recently, researchers set an ambitious goal of conducting speaker recognition in unconstrained conditions where The dataset is free for researchers and can be downloaded from. The dataset also involves a development set that can be used to boost the performance of AVPR systems in real-life situations. A comprehensive study was conducted to compare CN-Celeb-AV with two popular public AVPR benchmark datasets, and the results demonstrated that CN-Celeb-AV is more in line with real-world scenarios and can be regarded as a new benchmark dataset for AVPR research. In particular, we put more emphasis on two real-world complexities: (1) data in multiple genres (2) segments with partial information. This dataset contains more than 420k video segments from 1,136 persons from public media. To meet the request for research on AVPR in unconstrained conditions, this paper presents a multi-genre AVPR dataset collected `in the wild', named CN-Celeb-AV.
However, most datasets used for AVPR research so far are collected in constrained environments, and thus cannot reflect the true performance of AVPR systems in real-world scenarios. Audio-visual person recognition (AVPR) has received extensive attention.
0 kommentar(er)
