The Transducer (e.g. RNN-Transducer or Conformer-Transducer) generates an output label sequence as it traverses the input sequence. It is straightforward to use in streaming mode, where it generates partial hypotheses before the complete input has been seen. This makes it popular in speech recognition. However, in streaming mode the Transducer has a mathematical flaw which, simply put, restricts the model's ability to change its mind. The fix is to replace local normalisation (e.g. a softmax) with global normalisation, but then the loss function becomes impossible to evaluate exactly. A recent paper proposes to solve this by approximating the model, severely degrading performance. Instead, this paper proposes to approximate the loss function, allowing global normalisation to apply to a state-of-the-art streaming model. Global normalisation reduces its word error rate by 9-11% relative, closing almost half the gap between streaming and lookahead mode.

翻译：编码器-解码器转换器（如RNN-Transducer或Conformer-Transducer）在遍历输入序列时生成输出标签序列。该模型在流式模式下易于使用，可在完整输入尚未呈现之前生成部分假设，因此被广泛应用于语音识别领域。然而，流式模式下的转换器存在数学缺陷——简而言之，限制了模型改变决策的能力。解决方案是将局部归一化（如softmax）替换为全局归一化，但此时损失函数无法精确计算。近期论文提出通过近似模型来解决该问题，但这会严重降低性能。相反，本文提出对损失函数进行近似，使得全局归一化可应用于先进的流式模型。全局归一化使词错误率相对降低9-11%，几乎缩小了流式模式与前瞻模式之间一半的差距。