We present our transducer model on Librispeech. We study variants to include an external language model (LM) with shallow fusion and subtract an estimated internal LM. This is justified by a Bayesian interpretation where the transducer model prior is given by the estimated internal LM. The subtraction of the internal LM gives us over 14% relative improvement over normal shallow fusion. Our transducer has a separate probability distribution for the non-blank labels which allows for easier combination with the external LM, and easier estimation of the internal LM. We additionally take care of including the end-of-sentence (EOS) probability of the external LM in the last blank probability which further improves the performance. All our code and setups are published.
翻译:我们在Librispeech上展示了我们的传感器模型。 我们研究变量, 以包括外语模型(LM), 有浅聚变, 并减去内部估计的LM。 一种巴伊西亚解释证明这一点是合理的, 估计内部LM给出了先前的传感器模型。 内部LM的减值让我们比正常的浅聚变提高了14%以上。 我们的传感器对非空白标签的概率分布是分开的, 它使得与外部LM更容易组合, 并且更容易估计内部LM。 我们另外还注意将外部LM的末端概率(EOS)纳入最后的空白概率, 从而进一步提高了性能。 我们的所有代码和设置都公布了 。