arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02176cs.CL
收藏

Dynamic Encoder Transducer:一种灵活的解决方案,可在准确性和延迟之间进行权衡

Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency

Facebook AI

Yangyang Shi, Varun Nagaraja, Chunyang Wu, Jay Mahadeokar, Duc Le, Rohit Prabhavalkar, Alex Xiao, Ching-Feng Yeh, Julian Chan, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer

摘要:

提出了一种用于设备上语音识别的动态编码器换能器(DET)。一个DET模型可以扩展到具有不同计算能力的多个设备,而无需重新训练或微调。为了平衡准确性和延迟,DET分配不同的编码器来解码话语的不同部分。我们应用并比较了层丢弃和协作学习的DET训练。层丢弃方法在训练阶段随机丢弃编码器层,可以在解码时按需丢弃层。协作学习在一个模型中联合训练具有不同深度的多个编码器。Librispeech和内部数据的实验结果表明,DET提供了一个灵活的准确性和延迟权衡。Librispeech上的结果表明,DET中的全尺寸编码器相对地将相同尺寸基线的字出错率降低了8%以上。通过协作学习训练的DET中的轻量级编码器将模型大小减少了25%,但仍然获得与全尺寸基线相似的WER。DET通过为一个话语的开始部分分配一个轻量级编码器和为其余部分分配一个全尺寸编码器,在大型内部数据集上获得与基线模型相似的准确性和更好的延迟。

英文摘要:

We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or finetuning. To trading off accuracy and latency, DET assigns different encoders to decode different parts of an utterance. We apply and compare the layer dropout and the collaborative learning for DET training. The layer dropout method that randomly drops out encoder layers in the training phase, can do on-demand layer dropout in decoding. Collaborative learning jointly trains multiple encoders with different depths in one single model. Experiment results on Librispeech and in-house data show that DET provides a flexible accuracy and latency trade-off. Results on Librispeech show that the full-size encoder in DET relatively reduces the word error rate of the same size baseline by over 8%. The lightweight encoder in DET trained with collaborative learning reduces the model size by 25% but still gets similar WER as the full-size baseline. DET gets similar accuracy as a baseline model with better latency on a large in-house data set by assigning a lightweight encoder for the beginning part of one utterance and a full-size encoder for the rest.

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。

↑