• documentation
main content

pretrained models -凯发k8网页登录

transfer learning, sound classification, feature embeddings, pretrained audio deep learning networks

audio toolbox™ provides matlab® and simulink® support for pretrained audio deep learning networks. locate and classify sounds with yamnet and estimate pitch with crepe. extract vggish or openl3 feature embeddings to input to machine learning and deep learning systems. use i-vector systems to produce compact representations of audio signals for applications such as speaker recognition, verification, identification, and diarization. use to perform voice activity detection (vad).

using pretrained deep learning networks requires deep learning toolbox™. the audio toolbox pretrained networks are available in deep network designer (deep learning toolbox).

functions

extract vggish feature embeddings
vggishvggish neural network
preprocess audio for vggish feature extraction
classifysoundclassify sounds in audio signal
yamnetyamnet neural network
graph of yamnet audioset ontology
preprocess audio for yamnet classification
extract openl3 feature embeddings
openl3 neural network
preprocess audio for openl3 feature extraction
estimate pitch with deep learning neural network
crepe neural network
preprocess audio for crepe deep learning network
postprocess output of crepe deep learning network
pretrained speaker recognition system
ivectorsystemcreate i-vector system
detect boundaries of speech in audio signal using ai
voice activity detection (vad) neural network
preprocess audio for voice activity detection (vad) network
postprocess frame-based vad probabilities

blocks

extract vggish embeddings
preprocess audio for vggish feature extraction
vggish embeddings extraction network
classify sounds in audio signal
yamnet sound classification network
preprocess audio for yamnet classification
extract openl3 embeddings
preprocess audio for openl3 embeddings extraction
openl3 embeddings extraction network
estimate pitch with crepe deep learning neural network
crepe deep pitch estimation neural network
preprocess audio for crepe deep pitch estimation
postprocess output of crepe pitch estimation network

apps

deep network designerdesign, visualize, and train deep learning networks

topics


  • configure an experiment that compares the performance of multiple pretrained networks applied to a speech command recognition task using transfer learning.

  • (simulink support package for android devices)

    this example shows how to use the simulink® support package for android™ devices and a pretrained yamnet network to classify human voices.

related information



网站地图