HybridMouse: A Hybrid Convolutional-Recurrent Neural Network-Based Model for Identification of Mouse Ultrasonic Vocalizations.
HybridMouse: A Hybrid Convolutional-Recurrent Neural Network-Based Model for Identification of Mouse Ultrasonic Vocalizations.
复制标题
DOI：
10.3389/fnbeh.2021.810590
复制
发表时间：
2021
影响因子：
3
通讯作者：
Wagner S
中科院分区：
文献类型：
--
作者：
Goussha Y;Bar K;Netser S;Cohen L;Hel-Or Y;Wagner S
老鼠使用超声波发声（USV）来传达各种社会相关信息。这些发声受性别、年龄、紧张和情绪状态的影响，因此可以用来表征它。目前用于检测和分析鼠USVs的工具依赖于用户输入和图像处理算法来识别USVs，因此需要理想的记录环境。最近的工具，利用卷积神经网络模型来识别发声段执行好于后者，但不利用音频发声的顺序结构。另一方面，人类语音识别模型是明确为音频处理而设计的;它们将CNN模型的优势融入到递归模型中，使它们能够捕捉音频的序列性质。在这里，我们描述了HybridMouse软件：一种音频分析工具，它结合了卷积（CNN）和递归（RNN）神经网络，用于自动识别，标记和提取记录的USV。在对各种实验条件下记录的手动标记的音频文件进行训练后，HybridMouse在准确性和精度方面优于使用深度学习工具的最常用基准模型。此外，它不需要用户输入，并在恶劣的实验条件下对记录的USV进行可靠的检测和分析。我们认为HybrideMouse将加强对小鼠USV的分析，并促进其在科学研究中的应用。
Mice use ultrasonic vocalizations (USVs) to convey a variety of socially relevant information. These vocalizations are affected by the sex, age, strain, and emotional state of the emitter and can thus be used to characterize it. Current tools used to detect and analyze murine USVs rely on user input and image processing algorithms to identify USVs, therefore requiring ideal recording environments. More recent tools which utilize convolutional neural networks models to identify vocalization segments perform well above the latter but do not exploit the sequential structure of audio vocalizations. On the other hand, human voice recognition models were made explicitly for audio processing; they incorporate the advantages of CNN models in recurrent models that allow them to capture the sequential nature of the audio. Here we describe the HybridMouse software: an audio analysis tool that combines convolutional (CNN) and recurrent (RNN) neural networks for automatically identifying, labeling, and extracting recorded USVs. Following training on manually labeled audio files recorded in various experimental conditions, HybridMouse outperformed the most commonly used benchmark model utilizing deep-learning tools in accuracy and precision. Moreover, it does not require user input and produces reliable detection and analysis of USVs recorded under harsh experimental conditions. We suggest that HybrideMouse will enhance the analysis of murine USVs and facilitate their use in scientific research.
登录
查看更多内容
影响因子：
4.6
作者：
Burkett, Zachary D.;Day, Nancy F.;White, Stephanie A.
通讯作者：
White, Stephanie A.
影响因子：
7.6
作者：
Coffey, Kevin R.;Marx, Russell G.;Neumaier, John F.
通讯作者：
Neumaier, John F.
影响因子：
7.7
作者：
Neunuebel JP;Taylor AL;Arthur BJ;Egnor SE
通讯作者：
Egnor SE
影响因子：
3.7
作者：
Tachibana, Ryosuke O.;Kanno, Kouta;Okanoya, Kazuo
通讯作者：
Okanoya, Kazuo
影响因子：
7.7
作者：
Fonseca AH;Santana GM;Bosque Ortiz GM;Bampi S;Dietrich MO
通讯作者：
Dietrich MO