Spoken Language Identification with Deep Convolutional Neural Network and Data Augmentation

机译：具有深度卷积神经网络和数据增强的口语语言识别

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this paper, a spoken language detection system based on deep convolutional neural networks is presented. The neural network model is trained and tested on a speech dataset containing five languages. Speech signals are first converted into mel-spectrogram features and these features are fed into the deep convolutional neural network. Flattened outputs of the deep convolutional network are then fed into a recurrent layer, and a dense layer with softmax activation function is used as an output layer to predict the output language probabilities. This network results in 0.89 F1-score in our test data. We also used a data augmentation method, namely SpecAugment, which increased the F1-score to 0.94.

机译：本文介绍了一种基于深卷积神经网络的口语检测系统。神经网络模型在包含五种语言的语音数据集上培训并测试。语音信号首先转换为熔点分子特征，并且这些特征被馈送到深卷积神经网络中。然后将深度卷积网络的扁平输出送入复制层，并且使用软MAX激活功能的致密层用作输出层以预测输出语言概率。该网络在测试数据中导致0.89 F1分数。我们还使用了数据增强方法，即分类，从而将F1分数增加到0.94。

著录项

来源
《Signal Processing and Communications Applications Conference》|2020年|1-4|共4页
会议地点
作者
Can Korkut; Ali Haznedaroğlu; Levent M. Arslan;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Spectrogram; Convolutional neural networks; Speech recognition; Neural networks; Mel frequency cepstral coefficient; Emotion recognition; Visualization;

机译：频谱图;卷积神经网络;语音识别;神经网络;麦形抗肌射尖系数;情绪识别;可视化;

相似文献

外文文献
中文文献
专利

1. Application of Deep Convolutional Neural Networks in Attention-Deficit/Hyperactivity Disorder Classification: Data Augmentation and Convolutional Neural Network Transfer Learning [J] . Zhu Li, Chang Weike Journal of Medical Imaging and Health Informatics . 2019,第8期

机译：深度卷积神经网络在注意力缺陷/多动障碍分类中的应用：数据增强与卷积神经网络转移学习
2. Skin melanoma classification using ROI and data augmentation with deep convolutional neural networks [J] . Khalid M. Hosny, Mohamed A. Kassem, Mohamed M. Foaud Multimedia Tools and Applications . 2020,第33a34期

机译：皮肤黑色素瘤分类使用ROI和数据增强与深卷积神经网络
3. Towards highly accurate coral texture images classification using deep convolutional neural networks and data augmentation [J] . Gomez-Rios Anabel, Tabik Siham, Luengo Julian, Expert Systems with Application . 2019,第MARa期

机译：使用深度卷积神经网络和数据扩充实现高精度的珊瑚纹理图像分类
4. Convolutional Neural Networks with Data Augmentation for Classifying Speakers' Native Language [C] . Gil Keren, Jun Deng, Jouni Pohjalainen, Annual Conference of the International Speech Communication Association . 2016

机译：卷积神经网络，数据增强用于分类扬声器母语
5. Analysing the effects of data augmentation and free parameters for text classification with recurrent convolutional neural networks. [D] . Quijas, Jonathan K. 2017

机译：使用递归卷积神经网络分析数据扩充和自由参数对文本分类的影响。
6. Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network [O] . Seung Seog Han, Gyeong Hun Park, Woohyung Lim, -1

机译：深度神经网络在灰指甲诊断中显示出与皮肤科医生相当且通常优于皮肤病的性能：通过基于区域的卷积深度神经网络自动构建灰指甲数据集
7. Identification of Spoken Language from Webcast Using Deep Convolutional Recurrent Neural Networks [O] . Dong ZHU, Ming HUANG, Jing-jing YANG, 2019

机译：使用深度卷积经常性神经网络识别来自网络广播的口语语言
8. Application of Convolutional Neural Networks to Language Identification in Noisy Conditions [R] . Lei, Y, Ferrer, L, Lawson, A, 2014

机译：卷积神经网络在噪声条件下语言识别中的应用

Spoken Language Identification with Deep Convolutional Neural Network and Data Augmentation

摘要

著录项

相似文献

相关主题

期刊订阅