论文标题
无晶格的MMI适应自我监督预审计的声学模型
Lattice-Free MMI Adaptation Of Self-Supervised Pretrained Acoustic Models
论文作者
论文摘要
在这项工作中，我们提出了无晶格MMI（LFMMI），以监督自我监督预审计的声学模型的适应。我们在千小时未转录的LiblisPeech数据中预先一个变压器模型，然后在三个不同的数据集上对LFMMI进行监督适应。我们的结果表明，通过LFMMI进行微调，我们始终在清洁和其他测试库中获得10％和35.3％的相对提高（100h），分配板上的10.8％（300h），而Swahili（38h）（38h）（38h）（38h）和4.4％的相对提高了4.3％，而与基线培训的基线培训仅相比，在Tagalog（84H）上是4.4％。
In this work, we propose lattice-free MMI (LFMMI) for supervised adaptation of self-supervised pretrained acoustic model. We pretrain a Transformer model on thousand hours of untranscribed Librispeech data followed by supervised adaptation with LFMMI on three different datasets. Our results show that fine-tuning with LFMMI, we consistently obtain relative WER improvements of 10% and 35.3% on the clean and other test sets of Librispeech (100h), 10.8% on Switchboard (300h), and 4.3% on Swahili (38h) and 4.4% on Tagalog (84h) compared to the baseline trained only with supervised data.
