Efficient Trainable Front-Ends for Neural Speech Enhancement

Jonah Casebeer; Umut Isik; Shrikant Venkataramani; Arvindh Krishnaswamy

ICASSP 2020accepted0 citations

Efficient Trainable Front-Ends for Neural Speech Enhancement

Jonah Casebeer, Umut Isik, Shrikant Venkataramani, Arvindh Krishnaswamy

Abstract

Many neural speech enhancement and source separation systems operate in the time-frequency domain. Such models often benefit from making their Short-Time Fourier Transform (STFT) front-ends trainable. In current literature, these are implemented as large Discrete Fourier Transform matrices; which are prohibitively inefficient for low-compute systems. We present an efficient, trainable front-end based on the butterfly mechanism to compute the Fast Fourier Transform, and show its accuracy and efficiency benefits for low-compute neural speech enhancement models. We also explore the effects of making the STFT window trainable.

BibTeX

@inproceedings{icassp2020_efficienttrainab,
  title = {Efficient Trainable Front-Ends for Neural Speech Enhancement},
  author = {Jonah Casebeer and Umut Isik and Shrikant Venkataramani and Arvindh Krishnaswamy},
  booktitle = {ICASSP 2020},
  year = {2020}
}