Abstract | ||
---|---|---|
We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorithm which samples valid extensions and an approximate decoding algorithm. We experiment with the Wall Street Journal speech recognition task. Our LSD model achieves 12.9% WER compared to a character baseline of 14.8% WER. When combined with a convolutional network on the encoder, we achieve 9.6% WER. |
Year | Venue | DocType |
---|---|---|
2017 | ICLR | Conference |
Volume | Citations | PageRank |
abs/1610.03035 | 12 | 0.79 |
References | Authors | |
12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
William Chan | 1 | 357 | 24.67 |
Yu Zhang | 2 | 442 | 41.79 |
Quoc V. Le | 3 | 8501 | 366.59 |
Navdeep Jaitly | 4 | 2988 | 166.08 |