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 2001.00378cs.SDcs.LGeess.AS
收藏

语音处理中的深度表示学习:挑战、最新进展和未来趋势

Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends

University of Southern Queensland(南昆士兰大学);Data61, CSIRO(澳大利亚联邦科学与工业研究组织数据61中心);Queensland University of Technology (QUT)(昆士兰科技大学);Information Technology University, Punjab(旁遮普信息技术大学);Imperial College London(帝国理工学院);University of Augsburg(奥格斯堡大学)

Siddique Latif, Rajib Rana, Sara Khalifa, Raja Jurdak, Junaid Qadir, Björn W. Schuller

摘要:

语音处理的研究传统上认为,设计手工设计的声学特征(特征工程)的任务是一个独立的问题,从设计有效的机器学习(ML)模型的任务进行预测和分类决策。这种方法有两个主要缺点:首先,手工特征工程是繁琐的,需要人类知识;其次,设计的功能可能不是最好的目标。这促使了在语音社区中采用最近的趋势,朝向利用表示学习技术,该技术可以自动地学习输入信号的中间表示,该中间表示更好地适合手头的任务,并且因此导致改进的性能。随着深度学习(DL)的发展,表示学习的重要性也在增加,其中表示更有用,更少依赖于人类知识,这使得它非常有利于分类,预测,本文的主要贡献是提出了一个最新的,通过将分散在三个领域的研究整合在一起,对不同的语音表示学习技术进行了全面的数据和调查。不同的研究领域包括自动语音识别(ASR)、说话人识别(SR)和说话人情感识别(SER)。最近的评论已经进行了ASR,SR和SER,然而,这些都没有集中在表示学习从语音-一个差距,我们的调查旨在弥合。

英文摘要:

Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to make prediction and classification decisions. There are two main drawbacks to this approach: firstly, the feature engineering being manual is cumbersome and requires human knowledge; and secondly, the designed features might not be best for the objective at hand. This has motivated the adoption of a recent trend in speech community towards utilisation of representation learning techniques, which can learn an intermediate representation of the input signal automatically that better suits the task at hand and hence lead to improved performance. The significance of representation learning has increased with advances in deep learning (DL), where the representations are more useful and less dependent on human knowledge, making it very conducive for tasks like classification, prediction, etc. The main contribution of this paper is to present an up-to-date and comprehensive survey on different techniques of speech representation learning by bringing together the scattered research across three distinct research areas including Automatic Speech Recognition (ASR), Speaker Recognition (SR), and Speaker Emotion Recognition (SER). Recent reviews in speech have been conducted for ASR, SR, and SER, however, none of these has focused on the representation learning from speech -- a gap that our survey aims to bridge.

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。

↑