Synthesizing realistic videos according to a given speech is still an op...
Recently, handwritten Chinese character error correction has been greatl...
The problem of document structure reconstruction refers to converting di...
Table structure recognition is an indispensable element for enabling mac...
Table of contents (ToC) extraction aims to extract headings of different...
With the increasing popularity of voice-based applications, acoustic
eav...
It has already been observed that audio-visual embedding is more robust ...
Rotational speed is one of the important metrics to be measured for
cali...
To operate in real-world high-stakes environments, deep learning systems...
General accent recognition (AR) models tend to directly extract low-leve...
In Uyghur speech, consonant and vowel reduction are often encountered,
e...
Most IoT systems involve IoT devices, communication protocols, remote cl...
Consonant and vowel reduction are often encountered in Uyghur speech, wh...
Keyword wakeup technology has always been a research hotspot in speech
p...
Recently, recommender systems have achieved promising performances and b...
Internet of Things (IoT) has become the most promising technology for se...