A Comparison of Pooling Methods on LSTM Models for Rare Acoustic Event Classification
A Comparison of Pooling Methods on LSTM Models for Rare Acoustic Event Classification
复制标题
DOI：
10.1109/icassp40776.2020.9053150
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Chieh-Chi Kao;Ming Sun;Weiran Wang;Chao Wang
中科院分区：
文献类型：
--
作者：
Chieh-Chi Kao;Ming Sun;Weiran Wang;Chao Wang
声学事件分类（AEC）和声学事件检测（AED）是指检测音频中是否发生特定目标事件的任务。由于长短期记忆 (LSTM) 在各种语音相关任务中都能带来最先进的结果，因此它也被用作 AEC 的流行解决方案。本文重点研究 LSTM 模型在 AEC 任务上的动力学。它包括对 LSTM 记忆保留的详细分析，以及使用 170 万个具有不同信噪比的多个事件生成的混合片段对 LSTM 模型上的九种不同池化方法进行基准测试。本文重点理解：1）话语级分类准确率； 2）对话语中事件位置的敏感性。该分析是在 DCASE 2017 挑战赛中用于检测罕见声音事件的数据集上完成的。我们发现预测级别上的最大池化在分类准确性和对话语中事件位置的不敏感性方面在九种池化方法中表现最好。据作者所知，这是第一种专注于 AEC 任务的 LSTM 动力学的此类工作。
Acoustic event classification (AEC) and acoustic event detection (AED) refer to the task of detecting whether specific target events occur in audios. As long short-term memory (LSTM) leads to state-of-the-art results in various speech related tasks, it is employed as a popular solution for AEC as well. This paper focuses on investigating the dynamics of LSTM model on AEC tasks. It includes a detailed analysis on LSTM memory retaining, and a benchmarking of nine different pooling methods on LSTM models using 1.7M generated mixture clips of multiple events with different signal-to-noise ratios. This paper focuses on understanding: 1) utterance-level classification accuracy; 2) sensitivity to event position within an utterance. The analysis is done on the dataset for the detection of rare sound events from DCASE 2017 Challenge. We find max pooling on the prediction level to perform the best among the nine pooling approaches in terms of classification accuracy and insensitivity to event position within an utterance. To authors’ best knowledge, this is the first kind of such work focused on LSTM dynamics for AEC tasks.