返回
Identifying language from songs
DOI:10.1007/s11042-020-10163-6.png)
摘要
En 中文
Audio signal-based applications have significantly evolved over the last decade from speech recognizers to audio-based search engines, and healthcare is no exception. It also holds true when multimedia content needs to be analyzed. One of the most popular and rapidly increasing sources of multimedia is music that can be in either audio or video format. To efficiently retrieve data, such ever-increasing information demands for different indexing and categorization techniques. The automated song search engines can benefit largely from a language identifier that can segregate songs by the language used. In this paper, we propose to identify the language of songs using Line Spectral Frequency-Approximation Gradation (LSF-AG) features and an ensemble learning-based classification technique. Ensemble learning was used due to its better generalization ability. Using 70+ hours of data for three different languages: English, Bangla, and Hindi, in our experiments, we achieved the highest average accuracy of 98.61% that outperforms standard techniques. Further, the robustness of the system was tested by taking noisy datasets into account.
Keyword:
Language identification
Song
LSF-AG
Ensemble learning
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
Three-dimensional codes for simulating electron beam transport and free-electron laser operation including space-charge effects考虑空间电荷效应的三维电子束传输与自由电子激光运行模拟代码
Adverse drug reaction (ADR) monitoring in India and the postal survey as a useful tool for ADR detection印度的不良药物反应(ADR)监测及邮政调查作为一种检测ADR的有用工具
Internalization and Degradation of Human Chorionic Gonadotropin in Ovine Luteal Cells: Effects of Inhibitors of Transglutaminase*人绒毛膜促性腺激素在绵羊黄体细胞中的内化和降解:转谷氨酰胺酶抑制剂的效应*
Curriculum learning based approach for noise robust language identification using DNN with attention
Responses of Vegetation and Soil to Artificial Restoration Measures in Abandoned Gold Mining Areas in Altai Mountain, Northwest China
Diversity
IF0
Residual convolutional neural network with attentive feature pooling for end-to-end language identification from short-duration speech具有注意特征池的残差卷积神经网络,用于短时语音的端到端语言识别

