期刊
APPLIED SCIENCES-BASEL
卷 11, 期 12, 页码 -出版社
MDPI
DOI: 10.3390/app11125712
关键词
topic classification; automatic speech recognition; semi-supervised learning; semi-supervised training; Transformer and Causal Dilated Convolution Network
类别
资金
- National Office for Philosophy and Social Sciences Project Research on Cross-Modal Retrieval Model and Feature Extraction Based on Representation Learning [17BTQ062]
- Macao Science and Technology Development Fund under Macao Funding Scheme for Key RD Projects [0025/2019/AKP]
The TCDCN model proposed in this paper, based on the Transformer and Causal Dilated Convolutional Network framework, aims to address the audio event recognition problem in speech recognition. By adjusting model sound events, capturing time correlation, and effectively dealing with the sparsity of audio data, this model achieves better recognition results than classification using neural networks and other fusion methods.
Aiming at the audio event recognition problem of speech recognition, a decision fusion method based on the Transformer and Causal Dilated Convolutional Network (TCDCN) framework is proposed. This method can adjust the model sound events for a long time and capture the time correlation, and can effectively deal with the sparsity of audio data. At the same time, our dataset comes from audio clips cropped by YouTube. In order to reliably and stably identify audio topics, we extract different features and different loss function calculation methods to find the best model solution. The experimental results from different test models show that the TCDCN model proposed in this paper achieves better recognition results than the classification using neural networks and other fusion methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据