Deep learning has advanced the state of the art of single-channel speech separation. However, separation models may overfit the training data and generalization across datasets is still an open problem in real-world conditions with noise. In this paper we address the generalization problem with Mixup as data augmentation approach. Mixup creates new training examples from linear combinations of samples during mini-batch training. We propose four variations of Mixup and assess the improved generalization of a speech separation model, DPRNN, with cross-corpus evaluation on LibriMix, TIMIT and VCTK datasets. DPRNN allows efficient modelling of longer input sequences by splitting the learnt representation from input mixture segment into small chunks and performing intra and inter chunk operations iteratively. We show that training DPRNN with the proposed Data-only Mixup augmentation variation improves performance on an unseen dataset in noisy conditions when compared to the baseline SpecAugment augmented models, while having comparable performance on the source dataset.

Mixup Augmentation for Generalizable Speech Separation

Gastaldo P.;
2021-01-01

Abstract

Deep learning has advanced the state of the art of single-channel speech separation. However, separation models may overfit the training data and generalization across datasets is still an open problem in real-world conditions with noise. In this paper we address the generalization problem with Mixup as data augmentation approach. Mixup creates new training examples from linear combinations of samples during mini-batch training. We propose four variations of Mixup and assess the improved generalization of a speech separation model, DPRNN, with cross-corpus evaluation on LibriMix, TIMIT and VCTK datasets. DPRNN allows efficient modelling of longer input sequences by splitting the learnt representation from input mixture segment into small chunks and performing intra and inter chunk operations iteratively. We show that training DPRNN with the proposed Data-only Mixup augmentation variation improves performance on an unseen dataset in noisy conditions when compared to the baseline SpecAugment augmented models, while having comparable performance on the source dataset.
2021
978-1-6654-3288-7
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/1141938
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 4
social impact