Hash representation learning of multi-view heterogeneous data is the key...
The multi-modal hashing method is widely used in multimedia retrieval. I...
Model evolution and constant availability of data are two common phenome...
The BigCode community, an open-scientific collaboration working on the
r...
Learning the hash representation of multi-view heterogeneous data is an
...
AI-driven medical history-taking is an important component in symptom
ch...
As language models grow ever larger, the need for large-scale high-quali...
A framework performing Visual Commonsense Reasoning(VCR) needs to choose...
Inducing semantic representations directly from speech signals is a high...
In this study, we tackle massively multilingual grapheme-to-phoneme
conv...
Click-through rate (CTR) Prediction is of great importance in real-world...
Learning to capture feature relations effectively and efficiently is
ess...
The task of phone-to-audio alignment has many applications in speech
res...
An individual's variation in writing style is often a function of both s...
Generating synthesised singing voice with models trained on speech data ...
New words are regularly introduced to communities, yet not all of these ...
Minimal paths are considered as a powerful and efficient tool for bounda...
Smart contracts are the artifact of the blockchain that provide immutabl...
This study probes the phonetic and phonological knowledge of lexical ton...
The log-rank test is most powerful under proportional hazards (PH). In
p...
For speech research, ultrasound tongue imaging provides a non-invasive m...
This paper describes the UM-IU@LING's system for the SemEval 2019 Task 6...
A challenge in speech production research is to predict future tongue
mo...