Abstract
Automatic Speech Recognition (ASR) has undergone a profound transformation over the past decade, driven by advances in deep learning. This survey provides a comprehensive overview of the modern era of ASR, charting its evolution from traditional hybrid systems, such as Gaussian Mixture Model-Hidden Markov Models (GMM-HMMs) and Deep Neural Network-HMMs (DNN-HMMs), to the now-dominant end-to-end neural architectures. We systematically review the foundational end-to-end paradigms: Connectionist Temporal Classification (CTC), attention-based encoder-decoder models, and the Recurrent Neural Network Transducer (RNN-T), which established the groundwork for fully integrated speech-to-text systems. We then detail the subsequent architectural shift towards Transformer and Conformer models, which leverage self-attention to capture long-range dependencies with high computational efficiency. A central theme of this survey is the parallel revolution in training paradigms. We examine the progression from fully supervised learning, augmented by techniques like SpecAugment, to the rise of self-supervised learning (SSL) with foundation models such as wav2vec 2.0, which drastically reduce the reliance on transcribed data. Furthermore, we analyze the impact of largescale, weakly supervised models like Whisper, which achieve unprecedented robustness through massive data diversity. The paper also covers essential ecosystem components, including key datasets and benchmarks (e.g., LibriSpeech, Switchboard, CHiME), standard evaluation metrics (e.g., Word Error Rate), and critical considerations for real-world deployment, such as streaming inference, on-device efficiency, and the ethical imperatives of fairness and robustness. We conclude by outlining open challenges and future research directions.
Abstract (translated)
自动语音识别（ASR）在过去十年中经历了一场深刻的变革，这是由于深度学习的进步所推动的。本综述提供了现代ASR时代的全面概述，回顾了其从传统的混合系统（如高斯混合模型-隐马尔可夫模型（GMM-HMM）和深层神经网络-隐马尔可夫模型（DNN-HMM））到如今占主导地位的端到端神经架构的发展历程。我们系统地回顾了基础性的端到端范式：连接时间分类（CTC）、基于注意力的编码器-解码器模型以及循环神经网络转导器（RNN-T），这些范式为完全集成的语音到文本系统奠定了基础。随后，我们详细介绍了架构向变压器和卷积变压器模型转变的过程，这些模型利用自注意力机制来高效地捕捉长程依赖关系。本综述的一个中心主题是训练范式的平行革命。我们研究了从全监督学习（通过SpecAugment等技术增强）到基于wav2vec 2.0等基础模型的自我监督学习（SSL）的发展过程，这些方法极大地减少了对转录数据的依赖。此外，我们还分析了大规模弱监督模型（如Whisper）的影响，这些模型通过海量的数据多样性实现了前所未有的鲁棒性。论文还涵盖了关键生态系统组件，包括重要的数据集和基准测试（例如LibriSpeech、Switchboard、CHiME）、标准评估指标（例如单词错误率），以及在实际部署中至关重要的考虑因素，如流推理、设备效率及公平性和稳健性的伦理要求。最后，我们概述了开放性挑战与未来的研究方向。
URL
https://arxiv.org/abs/2510.12827
