当前位置：首页 > news >正文

音频分类的学习

news 来源：原创 2025/5/15 8:24:00

1.深度学习PyTorch入门-语音分类

https://blog.csdn.net/sinat_41787040/article/details/129795496

https://github.com/musikalkemist/pytorchforaudio

https://github1s.com/musikalkemist/pytorchforaudio/blob/main/04%20Creating%20a%20custom%20dataset/urbansounddataset.py

https://github.com/musikalkemist/DeepLearningForAudioWithPython

https://github.com/musikalkemist/AudioSignalProcessingForML

https://github.com/musikalkemist/generating-sound-with-neural-networks

https://github.com/musikalkemist/Deep-Learning-Audio-Application-From-Design-to-Deployment

https://github.com/yaokaishile/AudioClassifier

GitHub - carl03q/AudioClassifier: A CNN audio classifier via spectrogram images.

2.基于Pytorch实现声音的分类

https://blog.csdn.net/weixin_45277161/article/details/135185613

https://blog.csdn.net/qq_33200967/article/details/119830756

https://github.com/yeyupiaoling/AudioClassification-Pytorch

3.基于深度学习的各种音频分类pytorch实战

https://blog.csdn.net/weixin_45717863/article/details/136237419

https://github.com/ethanyhzhang/AudioClassification-Pytorch

4.Urbansound8k声音分类深度学习实战

GitHub - musikalkemist/pytorchforaudio: Code for the "PyTorch for Audio + Music Processing" series on The Sound of AI YouTube channel.

pytorchforaudio/09 Training urban sound classifier at main · musikalkemist/pytorchforaudio · GitHub

UrbanSound8K数据集

#wget命令下载

wget https://zenodo.org/record/1203745/files/UrbanSound8K.tar.gz

5.语音识别 - PyTorch实现

https://juejin.cn/post/7107844968957345805

6.音频识别(Audio Classification)学习笔记

https://blog.csdn.net/Killer_kali/article/details/122798462

7.基于Pytorch的声音事件检测分类系统

https://blog.csdn.net/weixin_43509698/article/details/145432599

https://github.com/Shybert-AI/AudioClassificationModelZoo-Pytorch

8.使用PyTorch进行城市声音分类

https://blog.csdn.net/gitblog_00081/article/details/139518564

https://github.com/ksanjeevan/crnn-audio-classification

9.torch入门：音频分类任务(pytorch+librosa)

https://blog.csdn.net/Ceverymxt7/article/details/146146361

10.PyTorch音频分类实战（完整代码）

https://blog.csdn.net/SoulmateY/article/details/143689699

https://blog.csdn.net/python1234_/article/details/145307536

https://zhuanlan.zhihu.com/p/6235637735

Github：github.com/Zeyi-Lin/Py…
数据集：pan.baidu.com/s/14CTI_9MD… 提取码: 1a9e
SwanLab实验日志：swanlab.cn/@ZeyiLin/Py…
更多实验日志：swanlab.cn/@ZeyiLin/Py…

Github：https://github.com/Zeyi-Lin/PyTorch-Audio-Classification
数据集：https://pan.baidu.com/s/14CTI_9MD1vXCqyVxmAbeMw?pwd=1a9e 提取码: 1a9e
SwanLab实验日志：https://swanlab.cn/@ZeyiLin/PyTorch_Audio_Classification-simple/charts
更多实验日志：https://swanlab.cn/@ZeyiLin/PyTorch_Audio_Classification/charts

11.使用深度学习进行音频分类的端到端示例和解释

https://blog.csdn.net/deephub/article/details/114997017

12.深度学习实现50种环境声音分类

https://blog.csdn.net/Mind_programmonkey/article/details/121024085

13.esc50

https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/esc50

https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/tutorial/cls/cls_tutorial.ipynb

14.CBAM与DenseNet121融合进行鸟类声音识别

https://blog.csdn.net/weixin_34945060/article/details/143473683

https://github.com/CarrieX6/-Xeno-Canto-

融合了CBAM与DenseNet121，使用中心损失函数及鸟声融合特征进行数据预处理、鸟声识别等任务

15.基于梅尔频谱的信号分类和识别

https://github.com/Friedrich-M/Audio-signal-classification-and-identification

数据集Urbansound8K

Urbansound8K是目前应用较为广泛的用于自动城市环境声分类研究的公共数据集，包含10个分类：空调声、汽车鸣笛声、儿童玩耍声、狗叫声、钻孔声、引擎空转声、枪声、手提钻、警笛声和街道音乐声。
数据集下载

16.使用BirdNET-V2.4训练自己的数据集

https://blog.csdn.net/weixin_53238517/article/details/144215320

https://github.com/birdnet-team/BirdNET-Analyzer/tree/training-with-test-data

https://github.com/birdnet-team/BirdNET-Analyzer

https://github.com/joeweiss/birdnetlib

15.鸟音频数据文件下载资源

https://hf-mirror.com/datasets/sakei/Bird_audio_in_China

https://hf-mirror.com/datasets/Trelis/bird-songs

https://github.com/DBD-research-group/BirdSet

A benchmark dataset collection for bird sound classification

https://hf-mirror.com/datasets/DBD-research-group/BirdSet

从huggingface上下载数据集具体步骤_huggingface 下载数据集-CSDN博客

eg:

git clone https://hf-mirror.com/datasets/DBD-research-group/BirdSet

git clone https://hf-mirror.com/datasets/sakei/Bird_audio_in_China

git clone https://hf-mirror.com/datasets/Trelis/bird-songs

https://zhuanlan.zhihu.com/p/701195734

使用ffmpeg提取视频中的音频并保存为单声道wav_ffmpeg wav-CSDN博客

https://zhuanlan.zhihu.com/p/452368276

birdData: 大批量，多线程下载鸟声文件

https://github.com/realzza/xenopy/tree/birdData

https://github.com/AgaMiko/xeno-canto-download

GitHub - AgaMiko/xeno-canto-download: Easy and ready-to-use script to download bird sound files and jsons from www.xeno-canto.org based on search terms.

鸟纲 Aves|iPlant 植物智——植物物种信息系统