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 2102.00291cs.SDcs.CLeess.AS
收藏

简单微调BERT的语音识别

Speech Recognition by Simply Fine-tuning BERT

Nagoya University(名古屋大学);Academia Sinica(中央研究院);National Taiwan University of Science and Technology(台湾科技大学)

Wen-Chin Huang, Chia-Hua Wu, Shang-Bao Luo, Kuan-Yu Chen, Hsin-Min Wang, Tomoki Toda

摘要:

我们提出了一种简单的自动语音识别(ASR)的方法,通过微调BERT,这是一个语言模型(LM)上训练的大规模未标记的文本数据,可以生成丰富的上下文表示。我们的假设是,给定一个历史上下文序列,一个强大的LM可以缩小可能的选择范围和语音信号可以作为一个简单的线索。因此,相比传统的ASR系统,训练一个强大的声学模型(AM)从头开始,我们相信,语音识别是可能的,通过简单地微调一个BERT模型。作为一个初步的研究,我们证明了所提出的想法的有效性AISHELL数据集,并表明堆叠一个非常简单的AM上的BERT可以产生合理的性能。

英文摘要:

We propose a simple method for automatic speech recognition (ASR) by fine-tuning BERT, which is a language model (LM) trained on large-scale unlabeled text data and can generate rich contextual representations. Our assumption is that given a history context sequence, a powerful LM can narrow the range of possible choices and the speech signal can be used as a simple clue. Hence, comparing to conventional ASR systems that train a powerful acoustic model (AM) from scratch, we believe that speech recognition is possible by simply fine-tuning a BERT model. As an initial study, we demonstrate the effectiveness of the proposed idea on the AISHELL dataset and show that stacking a very simple AM on top of BERT can yield reasonable performance.

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。

↑