openl3Features
The openl3Features
function will be removed in a future release. Use
openl3Embeddings
instead. For more information, see Compatibility Considerations.
Description
returns OpenL3 feature embeddings over time for audio input embeddings
= openl3Features(audioIn
,fs
)audioIn
with sample rate fs
. Columns of the input are treated as individual
channels.
specifies options using one or more embeddings
= openl3Features(audioIn
,fs
,Name,Value
)Name,Value
arguments. For
example, embeddings = openl3Features(audioIn,fs,'OverlapPercentage',75)
applies a 75% overlap between consecutive frames used to create the audio
embeddings.
This function requires both Audio Toolbox™ and Deep Learning Toolbox™.
Examples
Input Arguments
Output Arguments
References
[1] Cramer, Jason, et al. "Look, Listen, and Learn More: Design Choices for Deep Audio Embeddings." In ICASSP 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2019, pp. 3852-56. DOI.org (Crossref), doi:/10.1109/ICASSP.2019.8682475.
Extended Capabilities
Version History
Introduced in R2021aSee Also
openl3Preprocess
| openl3
| vggish
| classifySound
| vggishEmbeddings
| audioFeatureExtractor