Speaker Two: That's the letter t. It makes the t sound. Speaker One: t, t, tiger. Aahh! Speaker Two: t, t, tractor. Speaker One: That's the letter p. It makes the p ...
Abstract: Recently, pre-trained models with phonetic supervision have demonstrated their advantages for crosslingual speech recognition in data efficiency and information sharing across languages.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results