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 2403.01255cs.SDcs.AIeess.ASeess.SP
收藏

基于先进深度学习方法的自动语音识别:综述

Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey

University of Medea(梅德阿大学);University of Sciences and Technology Houari Boumediene (USTHB)(胡阿里·布迈丁科技大学);University of Dubai(迪拜大学)

Hamza Kheddar, Mustapha Hemis, Yassine Himeur

AI总结:

本综述系统回顾了基于深度迁移学习、联邦学习、强化学习及Transformer的自动语音识别框架,分析了各方法的优缺点与现有挑战,为未来研究提供方向。

摘要:

深度学习(DL)的最新进展给自动语音识别(ASR)带来了重大挑战。ASR依赖于包括机密数据在内的大量训练数据集,并需要大量的计算和存储资源。启用自适应系统可提升ASR在动态环境中的性能。DL技术假设训练和测试数据来自同一域,但这并非总是成立。诸如深度迁移学习(DTL)、联邦学习(FL)和强化学习(RL)等先进DL技术可解决这些问题。DTL允许使用小而相关的数据集实现高性能模型,FL使得无需持有数据集即可在机密数据上进行训练,而RL则优化动态环境中的决策,降低计算成本。本综述全面回顾了基于DTL、FL和RL的ASR框架,旨在提供对最新发展的见解,并帮助研究人员和专业人士理解当前挑战。此外,Transformer作为先进DL技术,在提出的ASR框架中被大量使用,因其能够捕获输入ASR序列中的广泛依赖关系,故本综述也对其进行了考虑。本文首先介绍DTL、FL、RL和Transformer的背景,然后采用精心设计的分类法概述最先进的方法。随后,进行批判性分析以识别每个框架的优势和劣势。此外,还进行了比较研究以突出现有挑战,为未来的研究机会铺平道路。

英文摘要:

Recent advancements in deep learning (DL) have posed a significant challenge for automatic speech recognition (ASR). ASR relies on extensive training datasets, including confidential ones, and demands substantial computational and storage resources. Enabling adaptive systems improves ASR performance in dynamic environments. DL techniques assume training and testing data originate from the same domain, which is not always true. Advanced DL techniques like deep transfer learning (DTL), federated learning (FL), and reinforcement learning (RL) address these issues. DTL allows high-performance models using small yet related datasets, FL enables training on confidential data without dataset possession, and RL optimizes decision-making in dynamic environments, reducing computation costs. This survey offers a comprehensive review of DTL, FL, and RL-based ASR frameworks, aiming to provide insights into the latest developments and aid researchers and professionals in understanding the current challenges. Additionally, transformers, which are advanced DL techniques heavily used in proposed ASR frameworks, are considered in this survey for their ability to capture extensive dependencies in the input ASR sequence. The paper starts by presenting the background of DTL, FL, RL, and Transformers and then adopts a well-designed taxonomy to outline the state-of-the-art approaches. Subsequently, a critical analysis is conducted to identify the strengths and weaknesses of each framework. Additionally, a comparative study is presented to highlight the existing challenges, paving the way for future research opportunities.

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。

↑