Scaling Speech Enhancement in Unseen Environments with Noise Embeddings

10/26/2018

∙

by   Gil Keren, et al.

∙

0

∙

share

We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main enhancement subnetwork. Second, we scale the number of noise environments present at training time to 16,784 different environments. Experiment results show that both manipulations reduce word error rates of a pretrained speech recognition system and improve enhancement quality according to a number of performance measures. Specifically, our best model reduces the word error rate from 34.04 Enhanced audio samples can be found in https://speechenhancement.page.link/samples.