arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.07059cs.SDcs.AIcs.HCeess.AS
收藏

LSTM-CNN网络用于嘈杂环境中的音频签名分析

LSTM-CNN Network for Audio Signature Analysis in Noisy Environments

KineticAI Inc.(动能人工智能公司);Iran University of Science and Technology(伊朗科技大学)

Praveen Damacharla, Hamid Rajabalipanah, Mohammad Hosein Fakheri

AI总结:

本研究提出LSTM-CNN网络,在嘈杂环境中利用19000个样本估计同时说话者的数量与性别,训练/验证MSE约0.019/0.017,验证了概念可行性。

摘要:

在办公场所、展览会、商场、销售及工业用途中,自动统计人数并识别其性别有多种应用。尽管当前的语音检测方法在大多数情况下应能良好运行,但在多数场景中,除性别外,当前说话者的数量未知,且由于可能的类别众多,分类方法并不适用。在本研究中,我们聚焦于长短期记忆卷积神经网络(LSTM-CNN),以提取声音数据中与时间和/或频率相关的特征,从而在嘈杂环境中估计每帧同时活跃说话者的数量/性别。考虑到最大说话者数为10,我们使用了19000个音频样本,这些样本包含男性、女性及公共城市、工业情境、商场、展览会、工作场所和自然环境中的背景噪声的多种组合,用于学习目的。这一概念验证显示出有前景的性能,在检测数量和性别方面,训练/验证均方误差(MSE)约为0.019/0.017。

英文摘要:

There are multiple applications to automatically count people and specify their gender at work, exhibitions, malls, sales, and industrial usage. Although current speech detection methods are supposed to operate well, in most situations, in addition to genders, the number of current speakers is unknown and the classification methods are not suitable due to many possible classes. In this study, we focus on a long-short-term memory convolutional neural network (LSTM-CNN) to extract time and / or frequency-dependent features of the sound data to estimate the number / gender of simultaneous active speakers at each frame in noisy environments. Considering the maximum number of speakers as 10, we have utilized 19000 audio samples with diverse combinations of males, females, and background noise in public cities, industrial situations, malls, exhibitions, workplaces, and nature for learning purposes. This proof of concept shows promising performance with training/validation MSE values of about 0.019/0.017 in detecting count and gender.

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。

↑