A Wavenet for speech denoising

Descripció

• Dades relacionades

  https://github.com/drethage/speech-denoising-wavenet

• Resum

  Most speech processing techniques use magnitude spectrograms as front-end and are therefore by default discarding part of the signal: the phase. In order to overcome this limitation' we propose an end-to-end learning method for speech denoising based on Wavenet. The proposed model adaptation retains Wavenet's powerful acoustic modeling capabilities, while significantly reducing its time-complexity by eliminating its autoregressive nature. Specifically, the model makes use of non-causal, dilated convolutions and predicts target fields instead of a single target sample. The discriminative adaptation of the model we propose, learns in a supervised fashion via minimizing a regression loss. These modifications make the model highly parallelizable during both training and inference. Both quantitative and qualitative evaluations indicate that the proposed method is preferred over Wiener filtering, a common method based on processing the magnitude spectrogram.
  Llegir més + Llegir menys -

• Descripció

  Comunicació presentada a la IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) celebrat a Calgary (Canada) del 15 al 20 d'abril de 2018.

• DOI

  http://dx.doi.org/10.1109/ICASSP.2018.8462417

• Col·leccions

  Congressos (Departament de Tecnologies de la Informació i les Comunicacions)
Mostra el registre complet