基于梅尔频谱的音频信号分类识别(Pytorch)

综述类文章，适合入门
https://blog.csdn.net/lsb2002/article/details/134516317

梅尔频谱与MFCC

https://geek.csdn.net/65bc87ebb8e5f01e1e45beb7.html
https://blog.csdn.net/qq_39516859/article/details/80505981
https://panjinquan.blog.csdn.net/article/details/120601437
https://geek.csdn.net/65bc98c7b8e5f01e1e45d7b6.html
https://blog.csdn.net/shi_xin/article/details/118895620
https://blog.csdn.net/weixin_52734695/article/details/140740804
https://www.zhihu.com/question/342790663
https://blog.51cto.com/u_16213649/8947530
https://blog.csdn.net/weixin_73784131/article/details/147851999

深度学习PyTorch入门-语音分类（数据集：yesno）

小型数据集，可快速实验
https://tencentcloud.csdn.net/661352059c80ea0d226aadf3.html
https://docs.pingcode.com/ask/1178469.html
https://blog.csdn.net/weixin_39628405/article/details/112182797
https://blog.csdn.net/qq_33472146/article/details/90647055

基于NumPy手动实现：信号的分帧、加窗、傅里叶变换 / 逆变换、重建

语音信号预处理，绝佳入门
https://blog.csdn.net/qq_20163065/article/details/129652727
https://blog.csdn.net/qq_34941290/article/details/143722579
https://blog.csdn.net/u013250861/article/details/126274610

基于 pytorch 实现 语音识别 有代码有数据

google的speech_command数据集，也可直接用tensorflow实现
https://pythonwfyyqq.blog.csdn.net/article/details/125234104

基于Pytorch实现的声音分类

AudioClassification-Pytorch识别库，没啥意思，封装的太好了
https://blog.csdn.net/qq_33200967/article/details/119830756

【torchaudio】常用函数和类

torchaudio.load() 和 librosa.load()
https://blog.csdn.net/everysigleday/article/details/128144158
https://blog.csdn.net/weixin_43457608/article/details/139993022

PyTorch乐器声音音频识别应用

https://blog.csdn.net/brucexia/article/details/140927901
https://agi-way.blog.csdn.net/article/details/142665782
https://blog.51cto.com/u_16213449/10704852
https://weibaohang.blog.csdn.net/article/details/127414288
https://blog.csdn.net/meridian002/article/details/143019742

pytorch和弦声音识别

https://blog.csdn.net/qq_20163065/article/details/129652727