Self-supervised representation learning for speech often involves a
quan...
The artificial intelligence (AI) system designer for thermal comfort fac...
Acoustic word embeddings (AWEs) are vector representations such that
dif...
Models of acoustic word embeddings (AWEs) learn to map variable-length s...
How do neural networks "perceive" speech sounds from unknown languages? ...
Several variants of deep neural networks have been successfully employed...
While language identification is a fundamental speech and language proce...
Transformer-based language models achieve high performance on various ta...
Deep neural networks have been employed for various spoken language
reco...
State-of-the-art spoken language identification (LID) systems, which are...