ATCSpeechNet：一个用于空中交通管制系统的多语种端到端语音识别框架
ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems
摘要：
在本文中，一个多语种的端到端的框架，称为ATCSpeechNet，提出了解决的问题，在空中交通管制（ATC）系统的通信语音翻译成人类可读的文本。在该框架中，我们专注于将多语言自动语音识别（ASR）集成到一个模型中，在该模型中，开发了一个端到端的范例，将语音波形直接转换为文本，而无需任何特征工程或词典。为了弥补ATC挑战所带来的手工特征工程的不足，提出了一种语音表示学习（SRL）网络来从原始波形中捕获鲁棒的、有鉴别力的语音表示。采用自监督训练策略，从未标记的数据中优化SRL网络，并进一步预测语音特征，即，波到特征改进了一种端到端的架构来完成ASR任务，其中应用基于图素的建模单元来解决多语言ASR问题。针对ATC领域中转录样本较少的问题，采用基于掩码预测的无监督方法，通过特征到特征的过程，在未标记数据上对ASR模型的主干网络进行预训练。最后，通过将SRL与ASR集成，以监督的方式制定了端到端的多语言ASR框架，该框架能够在一个模型中将原始波转换为文本，即，波形转文字在ATCPeech语料库上的实验结果表明，该方法在标注语料量很小、资源消耗较少的情况下取得了很好的性能，在58小时的转录语料库上标注出错率仅为4.20%.与基线模型相比，该方法获得了超过100%的相对性能改善，并可以进一步提高转录样本的大小。
英文摘要：
In this paper, a multilingual end-to-end framework, called as ATCSpeechNet, is proposed to tackle the issue of translating communication speech into human-readable text in air traffic control (ATC) systems. In the proposed framework, we focus on integrating the multilingual automatic speech recognition (ASR) into one model, in which an end-to-end paradigm is developed to convert speech waveform into text directly, without any feature engineering or lexicon. In order to make up for the deficiency of the handcrafted feature engineering caused by ATC challenges, a speech representation learning (SRL) network is proposed to capture robust and discriminative speech representations from the raw wave. The self-supervised training strategy is adopted to optimize the SRL network from unlabeled data, and further to predict the speech features, i.e., wave-to-feature. An end-to-end architecture is improved to complete the ASR task, in which a grapheme-based modeling unit is applied to address the multilingual ASR issue. Facing the problem of small transcribed samples in the ATC domain, an unsupervised approach with mask prediction is applied to pre-train the backbone network of the ASR model on unlabeled data by a feature-to-feature process. Finally, by integrating the SRL with ASR, an end-to-end multilingual ASR framework is formulated in a supervised manner, which is able to translate the raw wave into text in one model, i.e., wave-to-text. Experimental results on the ATCSpeech corpus demonstrate that the proposed approach achieves a high performance with a very small labeled corpus and less resource consumption, only 4.20% label error rate on the 58-hour transcribed corpus. Compared to the baseline model, the proposed approach obtains over 100% relative performance improvement which can be further enhanced with the increasing of the size of the transcribed samples.
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。
