Domain Adaptation Approaches for Acoustic Modeling
2020 28TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU)(2020)
摘要
In the recent years, with the development of neural network based models, ASR systems have achieved a tremendous performance increase. However, this performance increase mostly depends on the amount of training data and the computational power. In a low-resource data scenario, publicly available datasets can be utilized to overcome data scarcity. Furthermore, using a pre-trained model and adapting it to the in-domain data can help with computational constraint. In this paper we have leveraged two different publicly available datasets and investigate various acoustic model adaptation approaches. We show that 4% word error rate can be achieved using a very limited in-domain data.
更多查看译文
关键词
Acoustic model adaptation, automatic speech recognition, artificial neural networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要