Paper ID | AUD-25.2 | ||
Paper Title | Real-time Speech Frequency Bandwidth Extension | ||
Authors | Yunpeng Li, Marco Tagliasacchi, Oleg Rybakov, Victor Ungureanu, Dominik Roblek, Google, Switzerland | ||
Session | AUD-25: Signal Enhancement and Restoration 2: Audio Coding and Restoration | ||
Location | Gather.Town | ||
Session Time: | Thursday, 10 June, 16:30 - 17:15 | ||
Presentation Time: | Thursday, 10 June, 16:30 - 17:15 | ||
Presentation | Poster | ||
Topic | Audio and Acoustic Signal Processing: [AUD-SEN] Signal Enhancement and Restoration | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | In this paper we propose a lightweight model for frequency bandwidth extension of speech signals, increasing the sampling frequency from 8kHz to 16kHz while restoring the high frequency content to a level almost indistinguishable from the 16kHz ground truth. The model architecture is based on SEANet (Sound EnhAncement Network), a wave-to-wave fully convolutional model, which uses a combination of feature losses and adversarial losses to reconstruct an enhanced version of the input speech. In addition, we propose a variant of SEANet that can be deployed on-device in streaming mode, achieving an architectural latency of 16ms. When profiled on a single core of a mobile CPU, processing one 16ms frame takes only 1.5ms. The low latency makes it viable for bi-directional voice communication systems. |