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 2202.01855cs.CLcs.SDeess.AS
收藏

基于随机投影量化器的自监督学习语音识别

Self-supervised Learning with Random-projection Quantizer for Speech Recognition

Google Research(谷歌研究院)

Chung-Cheng Chiu, James Qin, Yu Zhang, Jiahui Yu, Yonghui Wu

摘要:

提出了一种简单有效的自监督学习方法用于语音识别。该方法学习一个模型来预测掩蔽的语音信号,以随机投影量化器生成的离散标签的形式。特别地,量化器用随机初始化的矩阵投影语音输入,并且在随机初始化的码本中进行最近邻查找。在自监督学习期间,矩阵和码本都不更新。由于随机投影量化器没有经过训练,并且与语音识别模型分离,该设计使得该方法灵活,并且与通用语音识别架构兼容。在LibriSpeech上,我们的方法实现了与以前使用非流模型的自监督学习的工作相似的单词错误率,并且提供了比wav 2 vec 2.0和w2 v-BERT更低的单词错误率和延迟。在多语言任务上,该方法也比wav 2 vec 2.0和w2 v-BERT提供了显着的改进。

英文摘要:

We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict the masked speech signals, in the form of discrete labels generated with a random-projection quantizer. In particular the quantizer projects speech inputs with a randomly initialized matrix, and does a nearest-neighbor lookup in a randomly-initialized codebook. Neither the matrix nor the codebook is updated during self-supervised learning. Since the random-projection quantizer is not trained and is separated from the speech recognition model, the design makes the approach flexible and is compatible with universal speech recognition architecture. On LibriSpeech our approach achieves similar word-error-rates as previous work using self-supervised learning with non-streaming models, and provides lower word-error-rates and latency than wav2vec 2.0 and w2v-BERT with streaming models. On multilingual tasks the approach also provides significant improvement over wav2vec 2.0 and w2v-BERT.

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。

↑