Main Content

本页的翻译已过时。点击此处可查看最新英文版本。

深度学习在音频处理领域的应用

利用音频和语音处理应用扩展深度学习工作流

通过将 Audio Toolbox™ 与 Deep Learning Toolbox™ 结合使用,将深度学习应用于音频和语音处理应用。有关信号处理应用,请参阅深度学习在信号处理领域的应用。有关无线通信中的应用,请参阅使用深度学习的无线通信

App

音频标注器(To be removed) Define and visualize ground-truth labels

函数

全部展开

audioDatastoreDatastore for collection of audio files
audioDataAugmenterAugment audio data
audioFeatureExtractorStreamline audio feature extraction
ivectorSystemCreate i-vector system
openl3Features(To be removed) Extract OpenL3 features
pitchnnEstimate pitch with deep learning neural network
vggishFeatures(To be removed) Extract VGGish features
classifySoundClassify sounds in audio signal
crepeCREPE neural network
crepePreprocessPreprocess audio for CREPE deep learning network
crepePostprocessPostprocess output of CREPE deep learning network
openl3OpenL3 neural network
openl3Features(To be removed) Extract OpenL3 features
openl3PreprocessPreprocess audio for OpenL3 feature extraction
pitchnnEstimate pitch with deep learning neural network
vggishVGGish neural network
vggishFeatures(To be removed) Extract VGGish features
vggishPreprocessPreprocess audio for VGGish feature extraction
yamnetYAMNet neural network
yamnetGraphGraph of YAMNet AudioSet ontology
yamnetPreprocessPreprocess audio for YAMNet classification

主题