论文标题
改进神经传感器的新培训管道
A New Training Pipeline for an Improved Neural Transducer
论文作者
论文摘要
RNN换能器是一个有希望的端到端模型候选者。我们将原始训练标准与所有对齐方式的全部边缘化进行了比较，与通常使用的最大近似值相比，这简化，改善和加快了我们的训练。我们还从原始的神经网络模型中概括，并研究更强大的模型，这是由于最大近似而成为可能的。我们进一步将输出标签拓扑概括为涵盖RNN-T，RNA和CTC。我们在所有这些方面进行了几项研究，包括对外部对齐影响的研究。我们发现，换能器模型在更长的序列上比注意模型更好。我们的最终换能器模型的表现优于我们的关注模型300h，相对相对较高6％。
The RNN transducer is a promising end-to-end model candidate. We compare the original training criterion with the full marginalization over all alignments, to the commonly used maximum approximation, which simplifies, improves and speeds up our training. We also generalize from the original neural network model and study more powerful models, made possible due to the maximum approximation. We further generalize the output label topology to cover RNN-T, RNA and CTC. We perform several studies among all these aspects, including a study on the effect of external alignments. We find that the transducer model generalizes much better on longer sequences than the attention model. Our final transducer model outperforms our attention model on Switchboard 300h by over 6% relative WER.
