Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Font, Marc Ferras"'
In recent years, many deep learning techniques for single-channel sound source separation have been proposed using recurrent, convolutional and transformer networks. When multiple microphones are available, spatial diversity between speakers and back
Externí odkaz:
http://arxiv.org/abs/2110.04047
In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with close-talk cl
Externí odkaz:
http://arxiv.org/abs/1807.11284
Publikováno v:
2015 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU); 1/1/2015, p289-295, 7p
Publikováno v:
2015 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU); 1/1/2015, pA1-A5, 5p