Abstract: Deep learning has made data-driven methods effective in underwater acoustic target recognition (UATR) using passive sonar signals. However, a major current challenge is the limited ...

Abstract: The modeling of human emotion expression in speech signals is an important, yet challenging task. The high resource demand of speech emotion recognition models, combined with the general ...

For nearly forty years, a strange signal has been drifting through the North Pacific, making scientists scratch their heads.

Takes a one-second WAV recording of a spoken digit (0..9) and transcribes it. The whole pipeline is a single neural network with a CTC loss, trained end-to-end on roughly 3,000 utterances in about 90 ...