Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions
INTERSPEECH, pp. 3785-3789, 2019.
We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our approach is a time-depth separable convolution block which dramatically reduces the number of parame...More
PPT (Upload PPT)