2 Hits in 2.7 sec

RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement [article]

Jalal Abdulbaqi, Yue Gu, Ivan Marsic
2019 arXiv   pre-print
We introduce an end-to-end fully-recurrent hourglass-shaped neural network architecture with residual connections for waveform-based single-channel speech enhancement.  ...  Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss.  ...  We, therefore, introduce our residual hourglass recurrent neural network (RHR-Net) for waveform-based single-channel speech enhancement.  ... 
arXiv:1904.07294v1 fatcat:a3mbqcpw4nd3lpzrfwr2wqb7py

Progressive loss functions for speech enhancement with deep neural networks

Jorge Llombart, Dayana Ribas, Antonio Miguel, Luis Vicente, Alfonso Ortega, Eduardo Lleida
2021 EURASIP Journal on Audio, Speech, and Music Processing  
AbstractThe progressive paradigm is a promising strategy to optimize network performance for speech enhancement purposes.  ...  This paper studies the progressive speech enhancement using convolutional and residual neural network architectures and explores two criteria for loss function optimization: weighted and uniform progressive  ...  Acknowledgements We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPU used for this research. This material is based upon work supported by Google Cloud.  ... 
doi:10.1186/s13636-020-00191-3 fatcat:vh5kulbekfgurmexjjaen6cera