# Translate Reverberated Speech to Anechoic Ones: Speech Dereverberation with BERT

arXiv: https://arxiv.org/abs/2007.08052 · HTML: https://mlsanity.com/paper/2007.08052/

## Key facts

- Cited by 1 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 16 Jul 2020.

## Built on by (most cited first, 1 of 1)

- [Tiny Transformers for Environmental Sound Classification at the Edge](https://mlsanity.com/paper/2103.12157/) (2021)

## Abstract (arXiv)

Single channel speech dereverberation is considered in this work. Inspired by the recent success of Bidirectional Encoder Representations from Transformers (BERT) model in the domain of Natural Language Processing (NLP), we investigate its applicability as backbone sequence model to enhance reverberated speech signal. We present a variation of the basic BERT model: a pre-sequence network, which extracts local spectral-temporal information and/or provides order information, before the backbone sequence model. In addition, we use pre-trained neural vocoder for implicit phase reconstruction. To evaluate our method, we used the data from the 3rd CHiME challenge, and compare our results with other methods. Experiments show that the proposed method outperforms traditional method WPE, and achieve comparable performance with state-of-the-art BLSTM-based sequence models.