基于对齐器-编码器的ASR的渐进对齐目标
Progressive Alignment Objectives for Aligner-Encoder based ASR
AI总结：
针对对齐器-编码器ASR模型中上层对齐突变导致训练不稳定的问题，提出InterAligner方法，通过中间对齐目标和CTC损失实现渐进对齐，在LibriSpeech上词错误率降至3.1/5.6。
摘要：
对齐器-编码器是最近提出的seq2seq端到端ASR模型，它通过直接从第u个编码器位置预测第u个token来替代解码器注意力，因此编码器必须在内部学习对齐，而无需交叉注意力或换能器格。在实践中，这种对齐通常在上层突然形成，使得训练对长语音敏感且脆弱。我们提出InterAligner，它添加了一个中间对齐器目标，使得对齐可以在深度上渐进形成，同时结合中间CTC损失（InterCTC）来稳定优化。在具有17层Conformer的LibriSpeech上，仅最终对齐器达到5.0/7.8的词错误率（test-clean/other）。InterCTC改进至3.4/6.0，而InterAligner进一步将词错误率降低至3.1/5.6，其中在长语音上收益最大。
英文摘要：
Aligner-Encoders are recently proposed seq2seq end-to-end ASR models that replace decoder attention by predicting the uth token directly from the u-th encoder position, so the encoder must learn the alignment internally without cross-attention or a transducer lattice. In practice, this alignment often forms abruptly in the upper layers, making training sensitive and brittle on long utterances. We propose InterAligner, which adds an intermediate Aligner objective so alignment can form progressively across depth, together with an intermediate CTC loss (InterCTC) to stabilize optimization. On LibriSpeech with a 17-layer Conformer, a final-only Aligner reaches 5.0/7.8 WER (test-clean/other). InterCTC improves to 3.4/6.0, and InterAligner further reduces WER to 3.1/5.6 with the largest gains on long utterances.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
