基于深度学习的音频情绪识别系统
Python 3.8
Keras & TensorFlow 2
用 LSTM、CNN、SVM、MLP 进行语音情感识别，Keras 实现。
识别准确率提高到了 80% 左右
TensorFlow 2 / Keras：LSTM & CNN (tensorflow.keras)
scikit-learn：SVM & MLP 模型，划分训练集和测试集
joblib：保存和加载用 scikit-learn 训练的模型
librosa：提取特征、波形图
SciPy：频谱图
pandas：加载特征
Matplotlib：绘图
NumPy
pip install -r requirements.txt
python preprocess.py --config configs/example.yaml
python train.py --config configs/example.yaml
python predict.py --config configs/example.yaml
import utils
utils.spectrogram(file_path)
文件下载
资源详情
[{"title":"（ 49 个子文件 75.75MB ） 基于深度学习的音频情绪识别系统","children":[{"title":"Speech-Emotion-Recognition-master","children":[{"title":"models","children":[{"title":"dnn","children":[{"title":"dnn.py <span style='color:#111;'> 4.04KB </span>","children":null,"spread":false},{"title":"cnn.py <span style='color:#111;'> 2.14KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 46B </span>","children":null,"spread":false},{"title":"lstm.py <span style='color:#111;'> 1.76KB </span>","children":null,"spread":false}],"spread":true},{"title":"ml.py <span style='color:#111;'> 2.69KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 1.23KB </span>","children":null,"spread":false},{"title":"base.py <span style='color:#111;'> 1.63KB </span>","children":null,"spread":false}],"spread":true},{"title":"features","children":[{"title":"7-category","children":[{"title":"train_opensmile_emodb.csv <span style='color:#111;'> 10.66MB </span>","children":null,"spread":false}],"spread":true},{"title":"6-category","children":[{"title":"librosa_casia","children":[{"title":"train.p <span style='color:#111;'> 3.03MB </span>","children":null,"spread":false}],"spread":true},{"title":"opensmile_savee_ravdess","children":[{"title":"train.csv <span style='color:#111;'> 29.40MB </span>","children":null,"spread":false}],"spread":true},{"title":"opensmile_casia","children":[{"title":"train.csv <span style='color:#111;'> 23.91MB </span>","children":null,"spread":false}],"spread":true},{"title":"opensmile_casia_is09","children":[{"title":"train.csv <span style='color:#111;'> 5.83MB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"3-category","children":[{"title":"train_opensmile_casia.csv <span style='color:#111;'> 23.91MB </span>","children":null,"spread":false},{"title":"train_opensmile_savee_ravdess.csv <span style='color:#111;'> 29.40MB </span>","children":null,"spread":false},{"title":"train_librosa_casia.p <span style='color:#111;'> 3.05MB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"README_EN.md <span style='color:#111;'> 7.23KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 1.44KB </span>","children":null,"spread":false},{"title":"predict.py <span style='color:#111;'> 1.16KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.06KB </span>","children":null,"spread":false},{"title":"extract_feats","children":[{"title":"librosa.py <span style='color:#111;'> 6.77KB </span>","children":null,"spread":false},{"title":"opensmile.py <span style='color:#111;'> 5.38KB </span>","children":null,"spread":false}],"spread":true},{"title":"preprocess.py <span style='color:#111;'> 397B </span>","children":null,"spread":false},{"title":"checkpoints","children":[{"title":"SVM_OPENSMILE_IS10.m <span style='color:#111;'> 11.27MB </span>","children":null,"spread":false},{"title":"CNN1D_LIBROSA_IS10.json <span style='color:#111;'> 4.81KB </span>","children":null,"spread":false},{"title":"LSTM_OPENSMILE_IS10.h5 <span style='color:#111;'> 3.38MB </span>","children":null,"spread":false},{"title":"CNN1D_LIBROSA_IS10.h5 <span style='color:#111;'> 1.28MB </span>","children":null,"spread":false},{"title":"MLP_OPENSMILE_IS10.m <span style='color:#111;'> 3.64MB </span>","children":null,"spread":false},{"title":"SCALER_OPENSMILE.m <span style='color:#111;'> 37.61KB </span>","children":null,"spread":false},{"title":"SCALER_LIBROSA.m <span style='color:#111;'> 7.84KB </span>","children":null,"spread":false},{"title":"MLP_LIBROSA_IS10.m <span style='color:#111;'> 757.25KB </span>","children":null,"spread":false},{"title":"CNN1D_OPENSMILE_IS10.json <span style='color:#111;'> 4.82KB </span>","children":null,"spread":false},{"title":"LSTM_LIBROSA_IS10.h5 <span style='color:#111;'> 917.14KB </span>","children":null,"spread":false},{"title":"LSTM_OPENSMILE_IS10.json <span style='color:#111;'> 2.09KB </span>","children":null,"spread":false},{"title":"SVM_LIBROSA_IS10.m <span style='color:#111;'> 2.15MB </span>","children":null,"spread":false},{"title":"CNN1D_OPENSMILE_IS10.h5 <span style='color:#111;'> 6.24MB </span>","children":null,"spread":false},{"title":"LSTM_LIBROSA_IS10.json <span style='color:#111;'> 2.09KB </span>","children":null,"spread":false}],"spread":false},{"title":"configs","children":[{"title":"cnn1d.yaml <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"lstm.yaml <span style='color:#111;'> 961B </span>","children":null,"spread":false},{"title":"svm.yaml <span style='color:#111;'> 860B </span>","children":null,"spread":false},{"title":"mlp.yaml <span style='color:#111;'> 836B </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 138B </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 2.13KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 6.94KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"__init__.py <span style='color:#111;'> 69B </span>","children":null,"spread":false},{"title":"plot.py <span style='color:#111;'> 2.92KB </span>","children":null,"spread":false},{"title":"files.py <span style='color:#111;'> 1.97KB </span>","children":null,"spread":false},{"title":"opts.py <span style='color:#111;'> 986B </span>","children":null,"spread":false}],"spread":true},{"title":".editorconfig <span style='color:#111;'> 188B </span>","children":null,"spread":false},{"title":".gitattributes <span style='color:#111;'> 66B </span>","children":null,"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- 电信商务领航NAV10-WF2-1 刷原厂教程+固件
- CLR via C#, 4th Edition.pdf 英文原版[非扫描版]
- DES加密算法（c语言实现）
- 海思35XX MPP构架和3798 UNF构架分析 - 副本.pdf
- C#winform网吧计费系统
- 图像加密matlab代码
- OpenGL超级宝典书第五版电子书+完整源码
- CMPP2.0JAVA调用
- keras_conv_lstm分类例子
- Iocomp.Instrumentation.WF40
- SQL数据库经典面试题(笔试题)
- 毕业设计—基于STC89C51单片机的模拟电梯设计
- 雅可比迭代C++实现
- 环信即时通讯单聊集成
- ScreenCaptureDemo.zip
- 订购180-源码
- 用户目录-源码
- LinuxAcademy_BlockchainEssentials：区块链基础知识课程中的说明-源码
- 更省app，省钱密令8数字07170717
- roboware安装包.2.tar.gz
- Java11安装程序包Windows64位版本.zip
- 计算机算法与分析五套试题汇总（含答案）
- 《鸟哥的Linux私房菜-基础篇》第四版 pdf
- 什么是极限学习机
- C#入门必看的实例程序100个
- VB.net 图书管理系统源代码
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明