arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2008.06208eess.AScs.CLcs.SD
收藏

Transformer ASR的自适应多领域语言模型

Adaptable Multi-Domain Language Model for Transformer ASR

Samsung Electronics(三星电子);Samsung Advanced Institute of Technology, Samsung Electronics(三星电子三星高级技术研究院)
Taewoo Lee, Min-Joong Lee, Tae Gyoon Kang, Seokyeoung Jung, Minseok Kwon, Yeona Hong, Jungin Lee, Kyoung-Gu Woo, Ho-Gyeong Kim, Jiseung Jeong, Jihyun Lee, Hosik… 展开作者

Taewoo Lee, Min-Joong Lee, Tae Gyoon Kang, Seokyeoung Jung, Minseok Kwon, Yeona Hong, Jungin Lee, Kyoung-Gu Woo, Ho-Gyeong Kim, Jiseung Jeong, Jihyun Lee, Hosik Lee, Young Sang Choi

摘要:

我们提出了一个基于适配器的多域Transformer语言模型(LM)的Transformer ASR。该模型包括一个大尺寸的普通LM和小尺寸的适配器。该模型仅使用较小的适配器及其相关层就可以实现多域适配。所提出的模型可以重用完整的微调LM,这是微调使用原始模型的所有层。所提出的LM可以扩展到新的域,增加约2%的参数的第一个域和13%的参数后,第二个域。所提出的模型也是有效的,在减少模型维护成本,因为它可以省略昂贵和耗时的共同LM预训练过程。使用建议的适配器为基础的方法,我们观察到,一个通用的LM与适配器可以胜过一个专用的音乐领域LM的字错误率(WER)。

英文摘要:

We propose an adapter based multi-domain Transformer based language model (LM) for Transformer ASR. The model consists of a big size common LM and small size adapters. The model can perform multi-domain adaptation with only the small size adapters and its related layers. The proposed model can reuse the full fine-tuned LM which is fine-tuned using all layers of an original model. The proposed LM can be expanded to new domains by adding about 2% of parameters for a first domain and 13% parameters for after second domain. The proposed model is also effective in reducing the model maintenance cost because it is possible to omit the costly and time-consuming common LM pre-training process. Using proposed adapter based approach, we observed that a general LM with adapter can outperform a dedicated music domain LM in terms of word error rate (WER).

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。

↑