论文标题
合奏中文端到端的口语理解是从音频流进行异常事件检测的
Ensemble Chinese End-to-End Spoken Language Understanding for Abnormal Event Detection from audio stream
论文作者
论文摘要
传统的口语理解（SLU）由两个阶段组成，第一阶段通过自动语音识别（ASR）映射到文本，以及第二阶段地图文本通过自然语言理解（NLU）意图。端到端SLU通过单个深度学习模型直接映射语音。以前的端到端SLU模型主要用于英语环境，因为缺少Chines中的大规模SLU数据集，并且仅使用一个ASR模型从语音中提取功能。在Kuaishou Technology的帮助下，收集了中文中的大型SLU数据集，以检测其现场音频流中的异常事件。基于此数据集，本文提出了用于中国环境的端到端集合模型。该集合SLU模型使用多个预训练的ASR模型提取了层次结构功能，从而更好地表示音素级别和单词级别信息。与以前的端到端SLU模型相比，这项拟议的方法可实现9.7％的准确性。
Conventional spoken language understanding (SLU) consist of two stages, the first stage maps speech to text by automatic speech recognition (ASR), and the second stage maps text to intent by natural language understanding (NLU). End-to-end SLU maps speech directly to intent through a single deep learning model. Previous end-to-end SLU models are primarily used for English environment due to lacking large scale SLU dataset in Chines, and use only one ASR model to extract features from speech. With the help of Kuaishou technology, a large scale SLU dataset in Chinese is collected to detect abnormal event in their live audio stream. Based on this dataset, this paper proposed a ensemble end-to-end SLU model used for Chinese environment. This ensemble SLU models extracted hierarchies features using multiple pre-trained ASR models, leading to better representation of phoneme level and word level information. This proposed approached achieve 9.7% increase of accuracy compared to previous end-to-end SLU model.
