口语理解中神经噪声信道模型的对比与一致性学习
Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding
AI总结：
针对口语理解中ASR错误导致的转录不一致问题，提出对比与一致性学习（CCL）方法，通过关联错误模式并强调潜在特征一致性，在四个基准数据集上提升了鲁棒性。
摘要：
近年来，深度端到端学习已被研究用于口语理解（SLU）中的意图分类。然而，端到端模型需要大量带有意图标签的语音数据，且高度优化的模型通常对训练与评估条件之间的不一致性敏感。因此，基于自动语音识别（ASR）的自然语言理解方法仍然具有吸引力，因为它可以利用预训练的通用语言模型，并适应语音输入环境的不匹配。采用这种基于模块的方法，我们改进了一个噪声信道模型，以处理由ASR错误引起的转录不一致性。我们提出了一种两阶段方法，即对比与一致性学习（CCL），该方法关联干净与带噪ASR转录之间的错误模式，并强调两种转录潜在特征的一致性。在四个基准数据集上的实验表明，CCL优于现有方法，并在各种噪声环境中提高了ASR鲁棒性。代码可在 https://github.com/syoung7388/CCL 获取。
英文摘要：
Recently, deep end-to-end learning has been studied for intent classification in Spoken Language Understanding (SLU). However, end-to-end models require a large amount of speech data with intent labels, and highly optimized models are generally sensitive to the inconsistency between the training and evaluation conditions. Therefore, a natural language understanding approach based on Automatic Speech Recognition (ASR) remains attractive because it can utilize a pre-trained general language model and adapt to the mismatch of the speech input environment. Using this module-based approach, we improve a noisy-channel model to handle transcription inconsistencies caused by ASR errors. We propose a two-stage method, Contrastive and Consistency Learning (CCL), that correlates error patterns between clean and noisy ASR transcripts and emphasizes the consistency of the latent features of the two transcripts. Experiments on four benchmark datasets show that CCL outperforms existing methods and improves the ASR robustness in various noisy environments. Code is available at https://github.com/syoung7388/CCL.
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。
