arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.04327cs.CLcs.AI
收藏

大词汇量设备上的双重学习ASR

Dual Learning for Large Vocabulary On-Device ASR

New York University(纽约大学);Google Inc.(谷歌公司)

Cal Peyser, Ronny Huang, Tara Sainath, Rohit Prabhavalkar, Michael Picheny, Kyunghyun Cho

摘要:

双学习是半监督机器学习的一种范式,它试图通过同时解决两个相反的任务来利用无监督数据。在该方案中,每个模型用于为未标记的示例生成伪标签,这些未标记的示例用于训练另一个模型。通过将ASR和TTS配对为双重任务,双重学习在语音处理中有一些用途。然而,这些结果大多只解决了使用非配对示例来补偿非常小的监督数据集的情况,并且大多数是在大型非流模型上。双学习尚未被证明可以有效地使用无监督数据来改进已经在大型监督语料库上训练的真实设备上的流模型。我们通过对在整个Librispeech上训练的设备大小的流一致性的分析来提供这个缺失的部分,显示出在没有LM的情况下相对WER提高了10.7%/5.2%,在LM的情况下相对WER提高了11.7%/16.4%。

英文摘要:

Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used to generate pseudo-labels for unlabeled examples that are used to train the other model. Dual learning has seen some use in speech processing by pairing ASR and TTS as dual tasks. However, these results mostly address only the case of using unpaired examples to compensate for very small supervised datasets, and mostly on large, non-streaming models. Dual learning has not yet been proven effective for using unsupervised data to improve realistic on-device streaming models that are already trained on large supervised corpora. We provide this missing piece though an analysis of an on-device-sized streaming conformer trained on the entirety of Librispeech, showing relative WER improvements of 10.7%/5.2% without an LM and 11.7%/16.4% with an LM.

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。

↑