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 1904.03416cs.LGcs.SDeess.ASstat.ML
收藏

从多个自监督任务中学习与问题无关的语音表示

Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks

Amazon Research(亚马逊研究院)

Santiago Pascual, Mirco Ravanelli, Joan Serrà, Antonio Bonafonte, Yoshua Bengio

摘要:

在没有监督的情况下学习良好的表示仍然是机器学习中的一个开放问题,并且对于语音信号尤其具有挑战性,语音信号通常以具有复杂分层结构的长序列为特征。然而,最近的一些工作表明,它是可能的,以获得有用的语音表示,采用自监督编码器-解码器的方法。本文提出了一种改进的自监督方法,其中单个神经编码器后面跟着多个工人,共同解决不同的自监督任务。不同任务之间所需的共识自然会对编码器施加有意义的约束,有助于发现一般表征并最大限度地减少学习肤浅表征的风险。实验表明,该方法可以学习可转移的,鲁棒的,和问题不可知的功能,进行相关信息的语音信号,如说话人身份,音素,甚至更高级别的功能,如情感线索。此外,许多设计选择使编码器易于出口,便于直接使用或适应不同的问题。

英文摘要:

Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some recent works, however, have shown that it is possible to derive useful speech representations by employing a self-supervised encoder-discriminator approach. This paper proposes an improved self-supervised method, where a single neural encoder is followed by multiple workers that jointly solve different self-supervised tasks. The needed consensus across different tasks naturally imposes meaningful constraints to the encoder, contributing to discover general representations and to minimize the risk of learning superficial ones. Experiments show that the proposed approach can learn transferable, robust, and problem-agnostic features that carry on relevant information from the speech signal, such as speaker identity, phonemes, and even higher-level features such as emotional cues. In addition, a number of design choices make the encoder easily exportable, facilitating its direct usage or adaptation to different problems.

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。

↑