arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.10407eess.AScs.LGcs.SD
收藏

在迁移学习中使用基于混合transformer-LSTM的端到端ASR利用文本数据

Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End ASR in Transfer Learning

Nanyang Technological University(南洋理工大学);Huya AI(虎牙人工智能);Nazarbayev University(纳扎尔巴耶夫大学);Alibaba Group(阿里巴巴集团)

Zhiping Zeng, Van Tung Pham, Haihua Xu, Yerbolat Khassanov, Eng Siong Chng, Chongjia Ni, Bin Ma

摘要:

在这项工作中,我们研究利用额外的文本数据来改善跨语言迁移学习设置下的低资源端到端ASR。为此,我们扩展了我们之前的工作[1],并提出了一个基于混合Transformer-LSTM的架构。这种架构不仅利用了Transformer网络的高效编码能力,而且由于基于LSTM的独立语言模型网络而受益于额外的文本数据。我们进行实验,我们内部的马来语语料库,其中包含有限的标记数据和大量的额外的文本。结果表明,当两者都使用有限的标记数据进行训练时,所提出的架构比以前基于LSTM的架构[1]的相对字错误率(WER)高出24.2%。从这一点出发,我们通过从另一种资源丰富的语言迁移学习,进一步获得了25.4%的相对WER降低。此外,我们通过使用额外的文本数据提升传输模型的LSTM解码器,获得了额外的13.6%的相对WER降低。总的来说,我们的最佳模型比普通Transformer ASR的相对WER高出11.9%。最后但并非最不重要的是,与LSTM和Transformer架构相比,所提出的混合架构提供了更快的推理。

英文摘要:

In this work, we study leveraging extra text data to improve low-resource end-to-end ASR under cross-lingual transfer learning setting. To this end, we extend our prior work [1], and propose a hybrid Transformer-LSTM based architecture. This architecture not only takes advantage of the highly effective encoding capacity of the Transformer network but also benefits from extra text data due to the LSTM-based independent language model network. We conduct experiments on our in-house Malay corpus which contains limited labeled data and a large amount of extra text. Results show that the proposed architecture outperforms the previous LSTM-based architecture [1] by 24.2% relative word error rate (WER) when both are trained using limited labeled data. Starting from this, we obtain further 25.4% relative WER reduction by transfer learning from another resource-rich language. Moreover, we obtain additional 13.6% relative WER reduction by boosting the LSTM decoder of the transferred model with the extra text data. Overall, our best model outperforms the vanilla Transformer ASR by 11.9% relative WER. Last but not least, the proposed hybrid architecture offers much faster inference compared to both LSTM and Transformer architectures.

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。

↑