Handling Background Noise in Neural Speech Generation
conference contributionposted on 28.06.2021, 07:41 by Tom Denton, Alejandro Luebs, Michael Chinen, Felicia SC Lim, Andrew Storus, Hengchin Yeh, Willem Kleijn, Jan Skoglund
Recent advances in neural-network based generative modeling of speech has shown great potential for speech coding. However, the performance of such models drops when the input is not clean speech, e.g., in the presence of background noise, preventing its use in practical applications. In this paper we examine the reason and discuss methods to overcome this issue. Placing a denoising preprocessing stage when extracting features and target clean speech during training is shown to be the best performing strategy.