HIGHLIGHTS
- who: DMITRII MUKHUTDINOV and colleagues from the (UNIVERSITY) have published the Article: Deep learning models for single-channel speech enhancement on drones, in the Journal: (JOURNAL)
- what: The authors show that time-frequency complex domain and UNet encoderdecoder architectures outperform other approaches on speech enhancement measures while providing a good trade-off with other criteria such as model size computation complexity and context length. The authors aim to understand how general DNN models perform when applied to the specific speech enhancement problem on drones. The authors evaluate speech enhancement performance of the models using perceptual . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.