利用多样化建模单元增强基于CTC的语音识别
Enhancing CTC-based speech recognition with diverse modeling units
AI总结：
本文研究基于CTC的语音识别中多样化建模单元的作用，提出E2E模型与音素、字素等单元联合训练的方法，揭示协同使用异构单元可显著提升ASR准确率。
摘要：
近年来，端到端（E2E）自动语音识别（ASR）模型的演进十分显著，这在很大程度上得益于Transformer等深度学习架构的进步。在E2E系统之上，研究者通过使用基于音素的模型对E2E模型的N-best假设进行重打分，取得了显著的准确率提升。这引出了一个有趣的问题：除了系统组合效应之外，这些改进究竟来自何处。我们考察了驱动这些增益的底层机制，并提出一种高效的联合训练方法，使E2E模型与多样化建模单元联合训练。该方法不仅协调了基于音素和基于字素模型各自的优势，还揭示了以协同方式使用这些多样化建模单元能够显著提升模型准确率。我们的发现为在开发更鲁棒、更准确的ASR系统过程中优化异构建模单元的集成提供了新的见解。
英文摘要：
In recent years, the evolution of end-to-end (E2E) automatic speech recognition (ASR) models has been remarkable, largely due to advances in deep learning architectures like transformer. On top of E2E systems, researchers have achieved substantial accuracy improvement by rescoring E2E model's N-best hypotheses with a phoneme-based model. This raises an interesting question about where the improvements come from other than the system combination effect. We examine the underlying mechanisms driving these gains and propose an efficient joint training approach, where E2E models are trained jointly with diverse modeling units. This methodology does not only align the strengths of both phoneme and grapheme-based models but also reveals that using these diverse modeling units in a synergistic way can significantly enhance model accuracy. Our findings offer new insights into the optimal integration of heterogeneous modeling units in the development of more robust and accurate ASR systems.
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。
